© 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. 79641
    Prev
    Next
    INDEX
    Explanations

    names of brands, companies, or specific products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    First syllables or initial portions of proper nouns, brand names, or specialized terms that appear when these entities are mentioned in text.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    Ỽt
    -0.08
     *</
    -0.08
     unl
    -0.08
    reste
    -0.07
    ÅĻÃŃzenÃŃ
    -0.07
    Æł
    -0.07
    *</
    -0.07
    (UINT
    -0.07
    egt
    -0.07
    ---</
    -0.07
    POSITIVE LOGITS
    aco
    0.07
    amb
    0.06
    icious
    0.06
    Question
    0.06
    æ°ı
    0.06
    mediately
    0.06
    levator
    0.06
    owski
    0.06
    uz
    0.06
    itecture
    0.06
    Activations Density 0.049%

    No Known Activations