© 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 EvalsExportsAPI 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. 29440
    Prev
    Next
    INDEX
    Explanations

    colons used for introducing lists or sections

    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
     zby
    -0.07
    ert
    -0.07
    926
    -0.06
    278
    -0.06
    ัà¸ģà¸ģ
    -0.06
     Sher
    -0.06
    auen
    -0.06
    aran
    -0.06
     totalement
    -0.06
    aur
    -0.06
    POSITIVE LOGITS
    à¤ķरण
    0.07
    urdy
    0.07
    .rdf
    0.06
    FTA
    0.06
    caler
    0.06
    ãĤ¸
    0.06
    Neal
    0.06
    ieux
    0.06
    851
    0.06
    WidgetItem
    0.06
    Activations Density 0.005%

    No Known Activations