© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 72789
    Prev
    Next
    INDEX
    Explanations

    references to household and family statistics

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    浩
    -0.07
    ali
    -0.06
    arget
    -0.06
    PMC
    -0.06
    ä¼ij
    -0.06
    åŁºåľ°
    -0.06
    IFO
    -0.06
    /Q
    -0.06
    ynes
    -0.06
     Misc
    -0.06
    POSITIVE LOGITS
    aldo
    0.06
     shar
    0.06
     íĬ
    0.06
    Sharing
    0.06
    /../
    0.06
     krev
    0.06
     Thornton
    0.06
    .raise
    0.06
     Ank
    0.06
    apia
    0.06
    Activations Density 0.000%

    No Known Activations