Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Llama3.1-8B-IT (Instruct)
Resid Post - 131k
11-RESID-POST-AA
130362
Prev
Next
MODEL
11-resid-post-aa
Source/SAE
INDEX
Go
Explanations
Chemical formulas
np_max-act · gemini-2.0-flash
No Scores
The neuron detects mentions of zinc (Zn) in chemical or biochemical compound names.
oai_token-act-pair · o4-mini
Triggered by @xinyanhu8
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
How To Load
Dataset (Dashboard)
Various
Features
131,072
Data Type
float32
Hook Name
blocks.11.hook_resid_post
Architecture
standard
Context Size
1,024
Dataset
monology/pile-uncopyrighted
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/llama3.1-8b-it/11-resid-post-aa/130362?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/llama3.1-8b-it/11-resid-post-aa/130362?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
-
-0.10
-
-0.07
---
-0.07
--
-0.06
"-
-0.06
-А
-0.06
'-
-0.06
효과
-0.06
MainMenu
-0.06
‐
-0.06
POSITIVE LOGITS
/S
0.10
/T
0.08
/F
0.08
/B
0.08
/C
0.08
/A
0.08
/h
0.08
/Y
0.08
(""));↵
0.07
,callback
0.07
Act
ivations
Density 0.042%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
