© 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 EvalsExportsinterp-engineNEWAPI 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. 28143
    Prev
    Next
    INDEX
    Explanations

    mentions of musical elements and personnel in a performance context

    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
    obe
    -0.07
    czy
    -0.07
    esus
    -0.07
    roys
    -0.07
    æķ
    -0.07
    vod
    -0.06
    _syntax
    -0.06
    imdi
    -0.06
    rie
    -0.06
    gratis
    -0.06
    POSITIVE LOGITS
    ADM
    0.06
     ocas
    0.06
    egg
    0.06
    ç±į
    0.06
     occasionally
    0.06
     himself
    0.06
    .timeScale
    0.06
     alternate
    0.06
    bor
    0.06
     Roger
    0.06
    Activations Density 0.004%

    No Known Activations