© 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. 38862
    Prev
    Next
    INDEX
    Explanations

    instances of the number zero

    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
    каÑģ
    -0.07
    à¤ľà¤¨
    -0.07
    uffman
    -0.07
    rana
    -0.07
    owler
    -0.07
    lém
    -0.06
    teri
    -0.06
    kul
    -0.06
    виÑĤ
    -0.06
    tere
    -0.06
    POSITIVE LOGITS
    istan
    0.07
    osc
    0.06
    ]={↵
    0.06
    mland
    0.06
    uisine
    0.06
     unge
    0.06
    ork
    0.06
    fix
    0.05
    .cond
    0.05
    wiki
    0.05
    Activations Density 0.000%

    No Known Activations