© 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. 104585
    Prev
    Next
    INDEX
    Explanations

    concepts related to games of chance and randomness

    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
    illez
    -0.08
     Checklist
    -0.07
    ptune
    -0.07
    iyon
    -0.07
     Bench
    -0.07
    bench
    -0.07
    zyst
    -0.06
    FRING
    -0.06
    paged
    -0.06
    ãģĭãģĦ
    -0.06
    POSITIVE LOGITS
    rale
    0.08
     draw
    0.07
     toss
    0.07
     opaque
    0.06
    SED
    0.06
    veal
    0.06
     Draw
    0.06
    /random
    0.06
    stral
    0.06
    åĨ³å®ļ
    0.06
    Activations Density 0.009%

    No Known Activations