© 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. 86481
    Prev
    Next
    INDEX
    Explanations

    references to spoilers in texts

    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
    istrovstvÃŃ
    -0.09
    baÅŁ
    -0.07
    .strict
    -0.07
    xed
    -0.07
    uars
    -0.07
    ibold
    -0.06
    retty
    -0.06
    TokenType
    -0.06
    enez
    -0.06
    moid
    -0.06
    POSITIVE LOGITS
     spo
    0.07
    yal
    0.07
    esc
    0.07
    icial
    0.07
    eting
    0.07
    GOR
    0.06
    aken
    0.06
    cial
    0.06
     Spoon
    0.06
    acus
    0.06
    Activations Density 0.010%

    No Known Activations