© 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. 80641
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries about possibilities or issues

    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
     sag
    -0.06
     Swan
    -0.06
     Sap
    -0.05
    phin
    -0.05
     Mata
    -0.05
     crystal
    -0.05
     fis
    -0.05
    ota
    -0.05
    SSF
    -0.05
    rome
    -0.05
    POSITIVE LOGITS
     somehow
    0.08
    ĵåIJį
    0.07
    aldi
    0.07
    oje
    0.07
    istar
    0.07
    åĪ¥
    0.07
    æŁĦ
    0.07
    elleicht
    0.06
    orizontal
    0.06
    787
    0.06
    Activations Density 0.012%

    No Known Activations