© 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. 30905
    Prev
    Next
    INDEX
    Explanations

    terms related to legal charges and assault

    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
     deaths
    -0.09
    _die
    -0.07
    ikal
    -0.07
     suicides
    -0.07
    Deaths
    -0.07
     death
    -0.07
     deadliest
    -0.07
     smrt
    -0.07
     Deaths
    -0.07
    _death
    -0.07
    POSITIVE LOGITS
     physical
    0.07
    ags
    0.07
     peace
    0.07
     verb
    0.07
     Physical
    0.06
     Violence
    0.06
    Physical
    0.06
     temper
    0.06
     physically
    0.06
    verb
    0.06
    Activations Density 0.019%

    No Known Activations