© 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. 86524
    Prev
    Next
    INDEX
    Explanations

    actions or behaviors that imply physical aggression or violence

    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
    aln
    -0.06
    COPE
    -0.06
    IST
    -0.06
    æĹĹ
    -0.06
     reception
    -0.06
    arendra
    -0.06
    ickets
    -0.06
    ilton
    -0.06
    NullOr
    -0.06
     spos
    -0.06
    POSITIVE LOGITS
    ela
    0.07
     cover
    0.07
     COVER
    0.07
    yle
    0.07
     $('#'
    0.06
    lep
    0.06
    cover
    0.06
    pit
    0.06
    uhl
    0.06
    argin
    0.06
    Activations Density 0.025%

    No Known Activations