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
78
Prev
Next
MODEL
25-res-jh
Source/SAE
INDEX
Go
Explanations
punctuation marks, specifically closing parentheses and brackets
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/78?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/78?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
1
-0.15
ÑĪи
-0.14
adv
-0.14
ings
-0.14
enz
-0.14
aw
-0.13
ï¼Īç¬ij
-0.13
Çİ
-0.13
way
-0.13
2
-0.13
POSITIVE LOGITS
s
0.73
Ùĩ
0.33
sik
0.30
ska
0.29
sak
0.27
ÏĤ
0.27
sheets
0.26
sing
0.26
sar
0.25
sav
0.25
Act
ivations
Density 0.138%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
