© 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. 42025
    Prev
    Next
    INDEX
    Explanations

    terms and genres related to various types of music

    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
    ysa
    -0.09
    antity
    -0.07
    ãĢ
    -0.07
    auer
    -0.07
    zas
    -0.07
     Ekon
    -0.06
    edium
    -0.06
    nar
    -0.06
    enum
    -0.06
    vely
    -0.06
    POSITIVE LOGITS
    tember
    0.07
     influences
    0.07
     elements
    0.07
     influence
    0.07
     aspects
    0.06
     backgrounds
    0.06
    Elements
    0.06
    isto
    0.06
    esk
    0.06
    mom
    0.06
    Activations Density 0.014%

    No Known Activations