© 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. 57447
    Prev
    Next
    INDEX
    Explanations

    elements related to contests and prizes

    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
    *)_
    -0.07
    idon
    -0.07
     Hab
    -0.07
    brains
    -0.07
     slash
    -0.06
     Pointer
    -0.06
     ifdef
    -0.06
    ifar
    -0.06
    ضÙĦ
    -0.06
    lg
    -0.06
    POSITIVE LOGITS
    quan
    0.07
     prize
    0.07
     gift
    0.07
     valued
    0.06
     donated
    0.06
    èĥľ
    0.06
    ÙĪرÛĮ
    0.06
    Value
    0.06
     Weinstein
    0.06
    restriction
    0.06
    Activations Density 0.003%

    No Known Activations