© 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. 123731
    Prev
    Next
    INDEX
    Explanations

    requests or phrases indicating the need for assistance or consideration

    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
    /mit
    -0.07
    imson
    -0.07
    ÄįnÃŃ
    -0.07
    feld
    -0.06
     multiplic
    -0.06
    олÑı
    -0.06
    eti
    -0.06
    atty
    -0.06
    compose
    -0.06
     Affero
    -0.06
    POSITIVE LOGITS
    enco
    0.08
    UnitOfWork
    0.06
    \Bundle
    0.06
     Thornton
    0.06
    ongyang
    0.06
     damages
    0.06
    ANO
    0.06
    estroy
    0.06
    LEY
    0.06
    idata
    0.06
    Activations Density 0.012%

    No Known Activations