© 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. 118670
    Prev
    Next
    INDEX
    Explanations

    references to the character "Sok" and related terms in discussions of narrative contexts

    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
    yne
    -0.08
    quam
    -0.07
     so
    -0.07
     Wick
    -0.06
    alus
    -0.06
    ouz
    -0.06
    coon
    -0.06
    ibling
    -0.06
    _SDK
    -0.06
     Fatal
    -0.06
    POSITIVE LOGITS
    ething
    0.10
    -called
    0.09
    etimes
    0.09
    ftware
    0.09
    theast
    0.08
     sánh
    0.08
    aking
    0.08
    onto
    0.07
    cial
    0.07
    ÑĢÑĥж
    0.07
    Activations Density 0.029%

    No Known Activations