© 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. 92492
    Prev
    Next
    INDEX
    Explanations

    references to education and learning opportunities

    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
    LineColor
    -0.07
    ãĢħ
    -0.07
    ieri
    -0.07
    ¨¨
    -0.06
    OKEN
    -0.06
    DAQ
    -0.06
    epend
    -0.06
    SAVE
    -0.06
    .types
    -0.06
    ucci
    -0.06
    POSITIVE LOGITS
     studying
    0.06
     sooner
    0.06
    Æ°á»Ľ
    0.06
    :frame
    0.06
    .son
    0.06
     transfer
    0.06
    andal
    0.06
    lac
    0.06
    uju
    0.06
     demanding
    0.06
    Activations Density 0.019%

    No Known Activations