© 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. 75109
    Prev
    Next
    INDEX
    Explanations

    mentions of prominent individuals or celebrities, particularly in contexts related to social issues or challenges they face

    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
    upert
    -0.07
    ernet
    -0.07
    achten
    -0.07
    irk
    -0.06
    uning
    -0.06
    Wake
    -0.06
    á»Ń
    -0.06
    vid
    -0.06
    aucoup
    -0.06
     Hav
    -0.06
    POSITIVE LOGITS
    -ves
    0.07
    elter
    0.06
    gerald
    0.06
    LK
    0.06
    icrous
    0.06
    ë¡ł
    0.06
     çģ
    0.06
    arian
    0.06
     Feinstein
    0.06
    ycle
    0.05
    Activations Density 0.039%

    No Known Activations