© 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. 97379
    Prev
    Next
    INDEX
    Explanations

    concepts related to legal regulations and liability

    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
    .EventQueue
    -0.06
     Jord
    -0.06
    ima
    -0.06
    inceton
    -0.06
    anga
    -0.06
    atsby
    -0.06
    ativ
    -0.06
    ician
    -0.06
     bat
    -0.06
     jenter
    -0.06
    POSITIVE LOGITS
    oten
    0.07
    หมาย
    0.07
    762
    0.07
     lạc
    0.07
    leet
    0.06
    Ïģιά
    0.06
    ennen
    0.06
     Fans
    0.06
    bern
    0.06
    109
    0.06
    Activations Density 0.026%

    No Known Activations