© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
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
Home
DeepSeek-R1-Dist-Llama-8B
17-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
23654
Prev
Next
MODEL
17-llamascope-slimpj-openr1-res-32k
Source/SAE
INDEX
Go
Explanations
phrases describing a situation or event as uncertain
oai_token-act-pair · gemini-2.0-flash
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L17R
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
Hzfinfdu/SlimPajama-3B and open-r1/OpenR1-Math-220k
Features
32,768
Data Type
float32
Hook Name
blocks.17.hook_resid_post
Architecture
jumprelu
Context Size
1,024
Dataset
cerebras/SlimPajama-627B
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/deepseek-r1-distill-llama-8b/17-llamascope-slimpj-openr1-res-32k/23654?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/deepseek-r1-distill-llama-8b/17-llamascope-slimpj-openr1-res-32k/23654?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
::↵
-0.07
``
-0.06
)↵
-0.06
''.
-0.06
DÄĽ
-0.06
“âĢ¦
-0.06
iá»ģm
-0.06
kop
-0.06
.''↵↵
-0.06
``
-0.06
POSITIVE LOGITS
[s
0.11
[$
0.10
[,]
0.09
[
0.09
[d
0.09
['
0.09
[\
0.09
[_
0.09
[y
0.08
[e
0.08
Act
ivations
Density 0.224%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
