© 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. 108180
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating a higher level or intensity

    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
    apeake
    -0.07
    ÑĨей
    -0.07
    kaar
    -0.07
    .sky
    -0.07
    insky
    -0.07
    .ds
    -0.06
    Ñĩин
    -0.06
    (æľ¨
    -0.06
     ----------------------------------------------------------------------↵
    -0.06
    ROTO
    -0.06
    POSITIVE LOGITS
    idian
    0.07
     mole
    0.06
    redo
    0.06
    uja
    0.06
    ¢ħ
    0.06
    há
    0.06
     ever
    0.06
    ulla
    0.06
    gid
    0.06
     Dez
    0.06
    Activations Density 0.013%

    No Known Activations