© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 75423
    Prev
    Next
    INDEX
    Explanations

    references to punching or physical aggression

    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
    534
    -0.07
    ieg
    -0.07
    'gc
    -0.07
     Holmes
    -0.07
    ipc
    -0.07
    ForMember
    -0.07
    oplay
    -0.06
    ÑĢава
    -0.06
    igate
    -0.06
    /ay
    -0.06
    POSITIVE LOGITS
     punching
    0.08
     punch
    0.08
    ardon
    0.08
     punched
    0.08
     holes
    0.07
    y
    0.07
    elog
    0.07
     fist
    0.07
     punches
    0.07
    лан
    0.07
    Activations Density 0.006%

    No Known Activations