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
OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
Llama3.1-8B
Residual Stream
24-LLAMASCOPE-RES-32K
7947
Prev
Next
MODEL
24-llamascope-res-32k
Source/SAE
INDEX
Go
Explanations
occurrences of the substring "Wa"
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
Comparing With
LLAMA3.1-8B @ 24-llamascope-res-32k
Configuration
fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
cerebras/SlimPajama-627B
Features
32,768
Data Type
bfloat16
Hook Name
blocks.24.hook_resid_post
Hook Layer
24
Architecture
jumprelu
Context Size
1,024
Dataset
cerebras/SlimPajama-627B
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/llama3.1-8b/24-llamascope-res-32k/7947?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/llama3.1-8b/24-llamascope-res-32k/7947?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
ment
-0.16
åij
-0.15
ÙħÙĨ
-0.15
ments
-0.15
udes
-0.15
меÑĩ
-0.15
کس
-0.15
olicit
-0.14
zar
-0.14
fy
-0.14
POSITIVE LOGITS
Wa
0.29
Wa
0.28
wa
0.26
WA
0.21
WA
0.18
wa
0.17
ifu
0.17
waiver
0.17
agner
0.17
ter
0.17
Act
ivations
Density 0.013%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
