© 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. 77446
    Prev
    Next
    INDEX
    Explanations

    key historical contributions and figures in feminist movements and intellectual history

    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
    .logic
    -0.07
    acente
    -0.07
    polator
    -0.07
    á»ijng
    -0.07
    ichert
    -0.07
    ÑĶм
    -0.07
    à¸ł
    -0.07
    okable
    -0.07
    versation
    -0.07
    ediator
    -0.07
    POSITIVE LOGITS
     today
    0.07
    125
    0.07
     principal
    0.06
    536
    0.06
     transition
    0.06
     prec
    0.06
     modern
    0.06
     proto
    0.06
     gen
    0.06
    转
    0.06
    Activations Density 0.014%

    No Known Activations