© 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. 86461
    Prev
    Next
    INDEX
    Explanations

    phrases associated with legal actions and consequences

    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
     Pine
    -0.07
    atta
    -0.07
    Äįel
    -0.07
    357
    -0.06
     laut
    -0.06
    pine
    -0.06
    Ìĥ
    -0.06
    stock
    -0.06
    427
    -0.06
     жиÑĢ
    -0.06
    POSITIVE LOGITS
    /actions
    0.08
    -actions
    0.07
     actions
    0.07
    æĮ¯ãĤĬ
    0.07
     acts
    0.06
     ActionType
    0.06
    estring
    0.06
    olics
    0.06
    Mvc
    0.06
    OnUiThread
    0.06
    Activations Density 0.045%

    No Known Activations