© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 5797
    Prev
    Next
    INDEX
    Explanations

    requests for user engagement or feedback

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    arez
    -0.08
     defaultManager
    -0.08
    ł
    -0.07
    å²³
    -0.07
    adal
    -0.07
    fillable
    -0.07
    heimer
    -0.07
    æ®
    -0.07
    aroo
    -0.07
    ÙĤØ·
    -0.07
    POSITIVE LOGITS
    0.06
     entr
    0.06
     tail
    0.06
    esor
    0.06
    im
    0.06
     bread
    0.05
     related
    0.05
    per
    0.05
    Bounding
    0.05
     Narrative
    0.05
    Activations Density 0.002%

    No Known Activations