© 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. 80530
    Prev
    Next
    INDEX
    Explanations

    specific references to locations or organizational entities

    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
    cz
    -0.07
    ousy
    -0.07
    memberof
    -0.07
    mino
    -0.06
    oui
    -0.06
    373
    -0.06
    ivals
    -0.06
    rage
    -0.06
    rof
    -0.06
    278
    -0.06
    POSITIVE LOGITS
     Tender
    0.07
    .edu
    0.07
    Ñĥмов
    0.07
    .sul
    0.06
    à¥įà¤Ĺत
    0.06
    ฯ
    0.06
     furn
    0.06
    俺
    0.06
     Sawyer
    0.06
    ibre
    0.06
    Activations Density 0.038%

    No Known Activations