© 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. 70303
    Prev
    Next
    INDEX
    Explanations

    programming constructs and structures related to functions and their parameters

    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
    баÑģ
    -0.08
    ãĤ¡
    -0.07
    .Companion
    -0.07
    tual
    -0.07
    _IOC
    -0.06
    egg
    -0.06
    ToPoint
    -0.06
     rast
    -0.06
    ReturnValue
    -0.06
    cdc
    -0.06
    POSITIVE LOGITS
    itionally
    0.07
    379
    0.06
    arily
    0.06
    ormal
    0.06
    ijing
    0.06
    919
    0.06
    ovich
    0.06
    irected
    0.06
    enso
    0.06
     false
    0.06
    Activations Density 0.032%

    No Known Activations