© 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. 30831
    Prev
    Next
    INDEX
    Explanations

    declarations and types related to unsigned integers

    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
    frei
    -0.08
    SEP
    -0.08
    riv
    -0.07
    ostat
    -0.07
    ough
    -0.07
    ÑģÑĭлки
    -0.07
    hani
    -0.07
    ISED
    -0.07
    ÑĢеÑĤ
    -0.07
    agus
    -0.07
    POSITIVE LOGITS
    ãĢħ
    0.06
    -wide
    0.06
    uu
    0.06
    imal
    0.06
    son
    0.06
    ucky
    0.06
    eger
    0.06
    pire
    0.06
    alysis
    0.06
    s
    0.06
    Activations Density 0.007%

    No Known Activations