© 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. 123243
    Prev
    Next
    INDEX
    Explanations

    references and citations within the text

    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
    thro
    -0.07
    illard
    -0.06
    meth
    -0.06
    @brief
    -0.06
    xac
    -0.06
    .hwp
    -0.06
    atatype
    -0.06
    fav
    -0.06
     defaultMessage
    -0.06
    olumn
    -0.06
    POSITIVE LOGITS
    References
    0.09
     bibliography
    0.09
     References
    0.09
     Foot
    0.09
     Bibli
    0.09
    _foot
    0.09
    references
    0.09
     references
    0.09
     foot
    0.08
     REFERENCES
    0.08
    Activations Density 0.018%

    No Known Activations