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
Julius Han · Gated SAE for Llama3-8B-Instruct
Llama3-8B-IT
Residual Stream
25-RES-JH
86
Prev
Next
MODEL
25-res-jh
Source/SAE
INDEX
Go
Explanations
phrases indicating an exit or removal from a situation
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Configuration
Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
How To Load
Features
65,536
Data Type
float32
Hook Name
blocks.25.hook_resid_post
Hook Layer
25
Architecture
gated
Context Size
1,024
Dataset
Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/llama3-8b-it/25-res-jh/86?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/llama3-8b-it/25-res-jh/86?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
é©
-0.15
hy
-0.15
idget
-0.15
idon
-0.14
nul
-0.14
plex
-0.14
hire
-0.14
ym
-0.14
acre
-0.14
illo
-0.14
POSITIVE LOGITS
ta
0.20
cast
0.18
Cold
0.18
Cold
0.18
smart
0.18
cold
0.17
of
0.17
cold
0.17
fox
0.17
casts
0.17
Act
ivations
Density 0.031%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
