Explain penultimate layer choice for trigger extraction

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

paper.log

@@ -1,4 +1,4 @@
-This is pdfTeX, Version 3.141592653-2.6-1.40.29 (TeX Live 2026/Arch Linux) (preloaded format=pdflatex 2026.3.11)  6 APR 2026 19:44
+This is pdfTeX, Version 3.141592653-2.6-1.40.29 (TeX Live 2026/Arch Linux) (preloaded format=pdflatex 2026.3.11)  6 APR 2026 19:46
 entering extended mode
  restricted \write18 enabled.
  %&-line parsing enabled.
@@ -429,7 +429,7 @@ File: umsb.fd 2013/01/14 v3.01 AMS symbols B
 ) [1
 
 {/var/lib/texmf/fonts/map/pdftex/updmap/pdftex.map}]
-Overfull \hbox (41.58173pt too wide) in paragraph at lines 118--122
+Overfull \hbox (41.58173pt too wide) in paragraph at lines 120--124
 \OT1/cmr/m/n/10.95 it (1536-dim, 35 lay-ers), E4B base (2560-dim, 42 lay-ers). 
 Quan-ti-za-tion tested at f32/f16/bf16/int8/int4
  []
@@ -440,18 +440,14 @@ Quan-ti-za-tion tested at f32/f16/bf16/int8/int4
 LaTeX2e <2025-11-01>
 L3 programming layer <2026-01-19>
  ***********
-
-
-LaTeX Warning: Label(s) may have changed. Rerun to get cross-references right.
-
 Package rerunfilecheck Info: File `paper.out' has not changed.
 (rerunfilecheck)             Checksum: 4198C661EF4EF302CF6CA8FE934684BD;2020.
  ) 
 Here is how much of TeX's memory you used:
- 12070 strings out of 467525
- 177761 string characters out of 5425861
- 607691 words of memory out of 5000000
- 40819 multiletter control sequences out of 15000+600000
+ 12071 strings out of 467525
+ 177779 string characters out of 5425861
+ 607805 words of memory out of 5000000
+ 40820 multiletter control sequences out of 15000+600000
  639085 words of font info for 84 fonts, out of 8000000 for 9000
  1141 hyphenation exceptions out of 8191
  75i,8n,79p,324b,557s stack positions out of 10000i,1000n,20000p,200000b,200000s
@@ -468,7 +464,7 @@ public/amsfonts/cm/cmr17.pfb></usr/share/texmf-dist/fonts/type1/public/amsfonts
 mf-dist/fonts/type1/public/amsfonts/cm/cmtt10.pfb></usr/share/texmf-dist/fonts/
 type1/public/amsfonts/cm/cmtt12.pfb></usr/share/texmf-dist/fonts/type1/public/c
 m-super/sfrm1095.pfb>
-Output written on paper.pdf (5 pages, 192843 bytes).
+Output written on paper.pdf (5 pages, 193342 bytes).
 PDF statistics:
  207 PDF objects out of 1000 (max. 8388607)
  168 compressed objects within 2 object streams

paper.md

@@ -23,7 +23,7 @@ Fine-tuning modifies weights. RAG re-encodes text each time. LoRA requires gradi
 **Frozen backbone**: any transformer. Produces hidden-state vectors from input tokens. Weights never modified.
 
 **Reflex bank**: stores (trigger, response) pairs:
-- **Trigger**: hidden-state vector h at the final token position — the model's activation pattern for a given input.
+- **Trigger**: hidden-state vector h at the final token position, extracted from the penultimate layer (N-1). The final layer is optimized for next-token prediction via the lm_head projection; earlier layers retain richer semantic structure for similarity matching.
 - **Response**: per-position logit biases [(token_id, boost)] — one pair per answer token.
 
 Both are sub-symbolic. The trigger is an opaque high-dimensional vector; the response is a list of (integer, float) pairs. The reflex bank resists inspection without the backbone that produced it.

paper.tex

@@ -63,7 +63,9 @@ input tokens. Weights never modified.
 \textbf{Reflex bank}: stores (trigger, response) pairs:
 \begin{itemize}
 \item \textbf{Trigger}: hidden-state vector $\mathbf{h}$ at the final token
-  position---the model's activation pattern for a given input.
+  position, extracted from the penultimate layer ($N{-}1$). The final layer is
+  optimized for next-token prediction via the lm\_head projection; earlier layers
+  retain richer semantic structure for similarity matching.
 \item \textbf{Response}: per-position logit biases
   $\{(t_i, b_i)\}$---one pair per answer token.
 \end{itemize}