© 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. 106862
    Prev
    Next
    INDEX
    Explanations

    references to lottery games and their characteristics

    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
    ugin
    -0.07
    .scalablytyped
    -0.07
    iddet
    -0.07
     Disconnect
    -0.07
    antz
    -0.07
    Disconnect
    -0.06
     Millet
    -0.06
    æĸŃ
    -0.06
    okino
    -0.06
    ÑĢиз
    -0.06
    POSITIVE LOGITS
    ample
    0.06
    EOS
    0.06
    rush
    0.06
    nds
    0.06
     integrity
    0.06
     plc
    0.06
    archives
    0.06
     bonus
    0.06
    dess
    0.06
    sa
    0.06
    Activations Density 0.009%

    No Known Activations