© 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. 62544
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    à¥Ģà¤ķरण
    -0.09
    ntax
    -0.07
    reater
    -0.07
    cce
    -0.07
    neau
    -0.07
    byt
    -0.06
     Alman
    -0.06
     scé
    -0.06
    cw
    -0.06
    опÑĢи
    -0.06
    POSITIVE LOGITS
    lov
    0.07
    appy
    0.06
    ALIGN
    0.06
    finity
    0.06
    à¸ŀล
    0.06
    ITES
    0.06
     maiden
    0.06
    afka
    0.06
    UEL
    0.06
    omore
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.