© 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. 81598
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific brand names

    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
    oire
    -0.07
    jab
    -0.06
    instein
    -0.06
    acious
    -0.06
    izzare
    -0.06
    icious
    -0.06
    adf
    -0.06
    /her
    -0.06
    hq
    -0.06
    theid
    -0.06
    POSITIVE LOGITS
    .Guna
    0.07
    #ac
    0.07
    elopment
    0.07
    swire
    0.07
    visited
    0.07
    ноÑģи
    0.07
    ÑĢади
    0.07
    çīĪ
    0.07
     Edition
    0.07
    verts
    0.07
    Activations Density 0.253%

    No Known Activations