© 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. 54600
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and fraudulent activities

    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
    ebek
    -0.08
     доÑĢ
    -0.07
    ExecutionContext
    -0.07
    Ïĩι
    -0.07
    .TestTools
    -0.07
    ίαÏĤ
    -0.07
    /commons
    -0.07
    nw
    -0.07
    çĿ£
    -0.07
    auer
    -0.06
    POSITIVE LOGITS
     actions
    0.10
     Actions
    0.08
     action
    0.08
     ACTIONS
    0.08
    actions
    0.08
    Actions
    0.07
     allegedly
    0.07
     activities
    0.07
     acts
    0.07
    action
    0.07
    Activations Density 0.031%

    No Known Activations