© 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. 62227
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to crime classification and penalties

    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
    amarin
    -0.07
     fav
    -0.06
    ieg
    -0.06
     lawsuits
    -0.06
    anguage
    -0.06
     i
    -0.06
    udies
    -0.06
    ulis
    -0.06
    istrat
    -0.06
    udy
    -0.05
    POSITIVE LOGITS
     conviction
    0.09
     convictions
    0.08
    conv
    0.07
     Conv
    0.07
    RITE
    0.07
     charged
    0.07
     aggravated
    0.07
     sécur
    0.07
    .conv
    0.07
     Habit
    0.07
    Activations Density 0.026%

    No Known Activations