© 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. 42174
    Prev
    Next
    INDEX
    Explanations

    terms related to odds or probabilities in gambling contexts

    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
    odyn
    -0.08
    indow
    -0.07
    HeaderValue
    -0.07
    .epsilon
    -0.07
    abaj
    -0.07
    :frame
    -0.07
    ushima
    -0.06
    ãĥ©ãĤ¯
    -0.06
    hra
    -0.06
    psilon
    -0.06
    POSITIVE LOGITS
     Snake
    0.07
    yat
    0.06
    acente
    0.06
    çĩķ
    0.06
    ment
    0.06
    ite
    0.06
     mort
    0.06
    SCRIBE
    0.06
    180
    0.06
     spins
    0.06
    Activations Density 0.000%

    No Known Activations