© 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. 4837
    Prev
    Next
    INDEX
    Explanations

    references to physical injuries and bodily harm

    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
     bruises
    -0.08
    ault
    -0.07
    Ã
    -0.07
    ingham
    -0.07
    OptionsResolver
    -0.07
    sume
    -0.07
    ofday
    -0.07
    ÑĤик
    -0.06
    rokes
    -0.06
    734
    -0.06
    POSITIVE LOGITS
     limbs
    0.07
     missing
    0.06
    ugen
    0.06
     left
    0.06
     whole
    0.06
    dej
    0.06
     irrig
    0.06
     entire
    0.06
    rowave
    0.06
     Ñħв
    0.06
    Activations Density 0.014%

    No Known Activations