© 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. 17-LLAMASCOPE-RES-131K
    11. 3322
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Woody."

    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
    mada
    -0.08
    apel
    -0.07
    iol
    -0.07
    lights
    -0.07
    ÛĮرÙĩ
    -0.07
    CardBody
    -0.07
    ØŃÙĦ
    -0.07
    Inspectable
    -0.07
    .fromFunction
    -0.07
    fixtures
    -0.07
    POSITIVE LOGITS
     Uns
    0.07
    osate
    0.07
     sho
    0.07
    ard
    0.06
    emia
    0.06
     uns
    0.06
    hausen
    0.06
    stock
    0.06
    ock
    0.06
    etes
    0.06
    Activations Density 0.003%

    No Known Activations