© 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. 30704
    Prev
    Next
    INDEX
    Explanations

    references to supplementary materials or sections in the document

    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
    avax
    -0.07
    lobal
    -0.07
    _Meta
    -0.07
     Sung
    -0.07
    forman
    -0.06
    ÙĦÛĮÙĦ
    -0.06
    fram
    -0.06
     sil
    -0.06
    .clients
    -0.06
    igaret
    -0.06
    POSITIVE LOGITS
    ove
    0.07
     dataSize
    0.07
    _online
    0.06
    Scaler
    0.06
    326
    0.06
     Online
    0.06
    jc
    0.06
    IALIZED
    0.06
    SCORE
    0.05
    /tutorial
    0.05
    Activations Density 0.017%

    No Known Activations