© 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 EvalsExportsAPI 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. 85544
    Prev
    Next
    INDEX
    Explanations

    references to imprisonment and its conditions

    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
    aho
    -0.07
    iska
    -0.07
    ENSE
    -0.07
    ensem
    -0.07
    à¤¾à¤ł
    -0.07
    bler
    -0.07
    è¾Ľ
    -0.06
    osal
    -0.06
    erah
    -0.06
    .returnValue
    -0.06
    POSITIVE LOGITS
     inmate
    0.07
     cell
    0.07
    auer
    0.07
     inmates
    0.07
     solitary
    0.07
     cells
    0.06
    lest
    0.06
    guards
    0.06
     Cell
    0.06
     Facility
    0.06
    Activations Density 0.054%

    No Known Activations