© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 119556
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to fraud and business practices

    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
    akin
    -0.07
    ktor
    -0.06
    ayload
    -0.06
     favorite
    -0.06
     roadway
    -0.06
     Bey
    -0.06
     Gow
    -0.05
     Cases
    -0.05
    ugar
    -0.05
    fram
    -0.05
    POSITIVE LOGITS
    mast
    0.09
    λλη
    0.07
     "[
    0.07
    važ
    0.07
    yš
    0.07
    ữa
    0.07
    tml
    0.07
    ITHER
    0.07
     :]
    0.07
    ãĥ»ãĥ»ãĥ»↵↵
    0.06
    Activations Density 0.011%

    No Known Activations