© 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. 9-LLAMASCOPE-RES-131K
    11. 94566
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement and legal terminology

    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
    vrier
    -0.07
    rais
    -0.07
    _TD
    -0.07
    loo
    -0.07
    utz
    -0.06
    /***/
    -0.06
    ëľ
    -0.06
     Tradable
    -0.06
     è¢
    -0.06
     Giang
    -0.06
    POSITIVE LOGITS
    stan
    0.06
    ãĥ¼ãĥIJ
    0.06
    went
    0.06
     Lamp
    0.06
    iversal
    0.06
     alike
    0.06
     typu
    0.06
    ved
    0.05
    Ž
    0.05
    .Expressions
    0.05
    Activations Density 0.000%

    No Known Activations