© 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. 73539
    Prev
    Next
    INDEX
    Explanations

    terms related to legal processes and immigration enforcement

    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
    /new
    -0.07
    oco
    -0.06
    hek
    -0.06
    áme
    -0.06
    Tes
    -0.06
    enu
    -0.06
    uzey
    -0.06
    ongo
    -0.06
    .nih
    -0.06
    Ïħκ
    -0.06
    POSITIVE LOGITS
     people
    0.09
     anyone
    0.09
     anybody
    0.09
     them
    0.08
     those
    0.07
     individuals
    0.07
     folk
    0.07
     suspected
    0.07
    plemented
    0.07
     suspect
    0.07
    Activations Density 0.034%

    No Known Activations