© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 729
    Prev
    Next
    INDEX
    Explanations

    statements made by police or officials regarding incidents or investigations

    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
    odi
    -0.07
    Invoker
    -0.07
    reau
    -0.07
     :</
    -0.06
     Anc
    -0.06
    lesson
    -0.06
     Tome
    -0.06
    _[
    -0.05
    idine
    -0.05
    оÑĢаз
    -0.05
    POSITIVE LOGITS
    à¥Ĥद
    0.07
     eoq
    0.07
    peon
    0.07
    eyh
    0.07
    leck
    0.06
    LOPT
    0.06
    DbType
    0.06
    nP
    0.06
    enco
    0.06
    OfType
    0.06
    Activations Density 0.005%

    No Known Activations