© 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. 41368
    Prev
    Next
    INDEX
    Explanations

    references to bonus content or additional material in media releases

    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
    Refresh
    -0.07
     decltype
    -0.07
     견
    -0.06
     Refresh
    -0.06
    BJECT
    -0.06
    yor
    -0.06
     freel
    -0.06
    Quote
    -0.06
    quir
    -0.06
     quote
    -0.06
    POSITIVE LOGITS
     extra
    0.13
     bonus
    0.12
     Bonus
    0.12
    bonus
    0.11
     extras
    0.10
    -extra
    0.10
    Bonus
    0.10
     exclusive
    0.10
     Extra
    0.10
    (extra
    0.10
    Activations Density 0.086%

    No Known Activations