© 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. 3711
    Prev
    Next
    INDEX
    Explanations

    references to athletes and their performance, particularly in relation to success, struggles, and potential future outcomes

    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
    :numel
    -0.07
    affer
    -0.06
    uchs
    -0.06
    wb
    -0.06
    Caption
    -0.06
    Soup
    -0.06
    avad
    -0.06
    acho
    -0.06
     Uses
    -0.06
    atis
    -0.06
    POSITIVE LOGITS
    кÑĥлÑı
    0.08
    ewith
    0.07
    should
    0.07
     should
    0.07
    lining
    0.07
    amak
    0.06
    elow
    0.06
     Placement
    0.06
    )((((
    0.06
     lẽ
    0.06
    Activations Density 0.042%

    No Known Activations