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
OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
Llama3.1-8B (Base)
Residual Stream
28-LLAMASCOPE-RES-32K
23139
Prev
Next
MODEL
28-llamascope-res-32k
Source/SAE
INDEX
Go
Explanations
programming-related terms and concepts, particularly around graphics and drawing functions
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
LLAMA3.1-8B @ 28-llamascope-res-32k
Configuration
fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-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.28.hook_resid_post
Hook Layer
28
Architecture
jumprelu
Context Size
1,024
Dataset
cerebras/SlimPajama-627B
Activation Function
relu
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/28-llamascope-res-32k/23139?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/28-llamascope-res-32k/23139?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
’↵
-0.20
‘
-0.17
“
-0.17
’.
-0.17
‘
-0.17
`.↵
-0.16
’.↵↵
-0.16
’,
-0.16
._↵
-0.16
ãĢı↵↵
-0.16
POSITIVE LOGITS
*/
0.52
*/
0.47
*/↵
0.43
*/↵↵
0.39
*/↵
0.38
*/↵↵
0.34
)*/↵
0.33
*/↵↵↵
0.32
}*/↵
0.32
}*/↵↵
0.30
Act
ivations
Density 0.053%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
