© 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 EvalsExportsAPI 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. 29094
    Prev
    Next
    INDEX
    Explanations

    articles that precede qualities, attributes, or descriptions

    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
     Bour
    -0.07
    undry
    -0.07
    iture
    -0.06
    ule
    -0.06
    ic
    -0.06
     themselves
    -0.06
    zo
    -0.06
     Co
    -0.06
    oute
    -0.06
    the
    -0.06
    POSITIVE LOGITS
    mite
    0.07
     pity
    0.07
    _ABI
    0.07
     raining
    0.07
    matter
    0.07
     matter
    0.07
    ssel
    0.07
    ayet
    0.07
    elu
    0.07
    gota
    0.07
    Activations Density 0.062%

    No Known Activations