Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Community
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
3-RESID-POST-AA
122450
Prev
Next
MODEL
3-resid-post-aa
Source/SAE
INDEX
Go
Explanations
に
np_max-act · gemini-2.0-flash
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_3/trainer_1
How To Load
Dataset (Dashboard)
Various
Features
131,072
Data Type
float32
Hook Name
blocks.3.hook_resid_post
Architecture
standard
Context Size
1,024
Dataset
monology/pile-uncopyrighted
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/llama3.1-8b-it/3-resid-post-aa/122450?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/llama3.1-8b-it/3-resid-post-aa/122450?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
ease
-0.07
adle
-0.07
orro
-0.06
Pragma
-0.06
iew
-0.06
cest
-0.06
trag
-0.06
ارز
-0.06
healing
-0.06
fd
-0.06
POSITIVE LOGITS
に
0.30
に
0.17
には
0.10
にも
0.10
いに
0.10
に見
0.09
日に
0.09
들에게
0.09
かに
0.09
りに
0.09
Act
ivations
Density 0.005%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
