© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 118642
    Prev
    Next
    INDEX
    Explanations

    concepts related to probabilities and chance in gaming scenarios

    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
     Kaynak
    -0.08
    ENTE
    -0.07
    pline
    -0.07
    icone
    -0.07
     Kraj
    -0.07
    ropp
    -0.07
    Multiply
    -0.07
    rompt
    -0.07
    qus
    -0.07
    tran
    -0.06
    POSITIVE LOGITS
     toss
    0.07
    -setup
    0.07
     tossed
    0.07
     outcomes
    0.07
     spins
    0.07
     odds
    0.06
     tossing
    0.06
    ges
    0.06
     spun
    0.06
    ollo
    0.06
    Activations Density 0.010%

    No Known Activations