© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87156
    Prev
    Next
    INDEX
    Explanations

    key phrases related to historical events and identities

    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
    isors
    -0.06
     дав
    -0.06
    ln
    -0.06
     ÙħÙĨÙĩا
    -0.06
    enia
    -0.06
    ereotype
    -0.06
    gressor
    -0.06
    elsing
    -0.06
    otion
    -0.06
    ftware
    -0.06
    POSITIVE LOGITS
    ãģĸ
    0.07
    URLException
    0.07
    HTTPHeader
    0.06
    UrlParser
    0.06
    _Exception
    0.06
    ImageContext
    0.06
    warnings
    0.06
    udos
    0.06
    otton
    0.06
     Morg
    0.06
    Activations Density 0.000%

    No Known Activations