© 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. 18002
    Prev
    Next
    INDEX
    Explanations

    code structure or formatting elements

    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
    alla
    -0.06
     ay
    -0.06
    idth
    -0.06
     Ay
    -0.06
     Temper
    -0.06
    crud
    -0.06
    rove
    -0.06
    ABS
    -0.06
    alama
    -0.05
    cht
    -0.05
    POSITIVE LOGITS
    icode
    0.08
    sted
    0.07
    istrovstvÃŃ
    0.07
    .utilities
    0.07
     domest
    0.07
    ystack
    0.07
    æ³ķ人
    0.07
    uido
    0.06
    ãĥĨãĥ«
    0.06
    endor
    0.06
    Activations Density 0.000%

    No Known Activations