© 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. 86473
    Prev
    Next
    INDEX
    Explanations

    elements related to news content or updates

    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
     pl
    -0.06
    Ĥ¨
    -0.06
    azine
    -0.06
    odore
    -0.06
    ajs
    -0.06
     ali
    -0.06
    ÏĢη
    -0.06
    èªł
    -0.06
     Lod
    -0.05
    loquent
    -0.05
    POSITIVE LOGITS
    commended
    0.07
     mocker
    0.07
    ponsored
    0.07
    /fixtures
    0.07
    Desk
    0.06
    inion
    0.06
    üme
    0.06
    ,...↵↵
    0.06
    ardon
    0.06
     Becker
    0.06
    Activations Density 0.004%

    No Known Activations