© 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. 107863
    Prev
    Next
    INDEX
    Explanations

    punctuation and separators in code or 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
    owan
    -0.07
    iteli
    -0.07
    itori
    -0.07
    iqueta
    -0.06
    ropp
    -0.06
    istrates
    -0.06
    ritos
    -0.06
    anken
    -0.06
    ataka
    -0.06
    iji
    -0.06
    POSITIVE LOGITS
    ">//
    0.07
    iken
    0.06
    ÑģÑĤи
    0.06
     Vital
    0.06
    Ïģαν
    0.06
     certif
    0.06
    ê¸ī
    0.06
    ç»ĻæĪij
    0.06
    }->{
    0.06
    á»ĩn
    0.06
    Activations Density 0.001%

    No Known Activations