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
DeepSeek-R1-Dist-Llama-8B
15-LLAMASCOPE-SLIMPJ-RES-32K
61
Prev
Next
MODEL
15-llamascope-slimpj-res-32k
Source/SAE
INDEX
Go
Explanations
phrases and indicators of prevalence and impact in discussions related to various subjects
oai_token-act-pair · gpt-4o-mini
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Configuration
fnlp/Llama-Scope-R1-Distill/800M-Slimpajama-0-OpenR1-Math-220k/L15R
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
Hzfinfdu/SlimPajama-3B
Features
32,768
Data Type
float32
Hook Name
blocks.15.hook_resid_post
Hook Layer
15
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/deepseek-r1-distill-llama-8b/15-llamascope-slimpj-res-32k/61?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/deepseek-r1-distill-llama-8b/15-llamascope-slimpj-res-32k/61?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
Both
-0.18
Both
-0.18
两人
-0.16
Neither
-0.16
both
-0.15
Neither
-0.15
BOTH
-0.15
vinc
-0.14
両
-0.14
neither
-0.14
POSITIVE LOGITS
all
0.26
none
0.22
all
0.21
hepsi
0.19
(all
0.18
none
0.18
-all
0.17
etc
0.17
etc
0.17
.all
0.17
Act
ivations
Density 0.362%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
