© 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. 55207
    Prev
    Next
    INDEX
    Explanations

    characters and decorative punctuation in text

    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
    aeda
    -0.07
    anzi
    -0.06
    pell
    -0.06
     impression
    -0.06
     merc
    -0.06
    /generated
    -0.06
     Labs
    -0.06
     ÑĸменÑĸ
    -0.06
    [src
    -0.06
    ög
    -0.06
    POSITIVE LOGITS
    .enterprise
    0.06
    noÅĽÄĩ
    0.06
    δά
    0.06
    erdale
    0.06
    flix
    0.06
    *)"
    0.06
    zen
    0.06
    dam
    0.06
    alking
    0.05
    áš
    0.05
    Activations Density 0.004%

    No Known Activations