© 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. 31379
    Prev
    Next
    INDEX
    Explanations

    information related to legal and contractual obligations

    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
     nackte
    -0.07
    fal
    -0.07
    μιÏĥ
    -0.07
     koc
    -0.07
    haf
    -0.06
    pras
    -0.06
    поÑģеÑĢед
    -0.06
    ↵↵
    -0.06
    dzi
    -0.06
    eer
    -0.06
    POSITIVE LOGITS
    utherford
    0.07
     Ravens
    0.07
    omb
    0.06
    ales
    0.06
    ixin
    0.06
    new
    0.06
    =YES
    0.06
    Ñİн
    0.06
    oug
    0.06
    izia
    0.06
    Activations Density 0.004%

    No Known Activations