© 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. 107530
    Prev
    Next
    INDEX
    Explanations

    legal terms and classifications related to homicide and manslaughter

    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
    057
    -0.06
     zer
    -0.06
     somehow
    -0.06
    raison
    -0.06
     Towers
    -0.06
     Fate
    -0.06
    orer
    -0.06
    ält
    -0.06
    -mounted
    -0.06
    ymb
    -0.06
    POSITIVE LOGITS
     maximum
    0.08
    ipi
    0.07
    maximum
    0.07
    ounty
    0.07
    olls
    0.07
     range
    0.07
    TextWriter
    0.06
    odzi
    0.06
    istrib
    0.06
    efeller
    0.06
    Activations Density 0.009%

    No Known Activations