© 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. 107403
    Prev
    Next
    INDEX
    Explanations

    expressions referring to personal or colloquial ownership

    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
    oui
    -0.07
    peg
    -0.06
    -coded
    -0.06
     Hicks
    -0.06
    ieten
    -0.06
    uci
    -0.06
     ظ
    -0.06
    yn
    -0.06
    rint
    -0.06
    Ãło
    -0.06
    POSITIVE LOGITS
     typical
    0.09
    иÑĦ
    0.07
     Typical
    0.07
    typ
    0.07
    -your
    0.06
    åħ¸
    0.06
    /Dk
    0.06
    _tokenize
    0.06
    bung
    0.06
    ixon
    0.06
    Activations Density 0.019%

    No Known Activations