© 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. 76154
    Prev
    Next
    INDEX
    Explanations

    descriptors related to personality or character traits

    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
     Sullivan
    -0.07
    erm
    -0.06
     Aires
    -0.06
    hl
    -0.06
     Ones
    -0.06
    olley
    -0.06
    ones
    -0.05
    upe
    -0.05
    elsing
    -0.05
     Olsen
    -0.05
    POSITIVE LOGITS
    ottes
    0.07
    оÑĤов
    0.07
    eldorf
    0.07
    заб
    0.07
    ibold
    0.07
    éĨ
    0.07
    ubat
    0.07
    .exc
    0.07
    meden
    0.07
    relude
    0.07
    Activations Density 0.000%

    No Known Activations