© 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. 14601
    Prev
    Next
    INDEX
    Explanations

    references to professionals in the entertainment industry, particularly actors and musicians

    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
    omic
    -0.07
    azzi
    -0.06
    assic
    -0.06
    ashtra
    -0.06
    ìķ½
    -0.06
    pec
    -0.06
    QObject
    -0.06
    cly
    -0.06
    stery
    -0.06
    hec
    -0.06
    POSITIVE LOGITS
    enez
    0.08
    [now
    0.07
    USIC
    0.07
    960
    0.06
    assin
    0.06
     apprec
    0.06
    inline
    0.06
    .partial
    0.06
    ëĵľë¦¬
    0.06
    .look
    0.06
    Activations Density 0.010%

    No Known Activations