© 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. 87358
    Prev
    Next
    INDEX
    Explanations

    numerical values, specifically those relating to scoring or measurements in a competitive context

    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
    ól
    -0.07
    iola
    -0.07
    uzzi
    -0.07
    /Dk
    -0.07
    ovi
    -0.07
    ãģ¹ãģį
    -0.07
    oyer
    -0.07
    æľ
    -0.07
     нада
    -0.07
     Ekon
    -0.07
    POSITIVE LOGITS
     ÑĢаÑħÑĥнок
    0.07
    celik
    0.06
     twice
    0.06
    uste
    0.06
    yg
    0.06
     Twice
    0.06
    اÙĬÙĨ
    0.05
     bay
    0.05
    ĵ
    0.05
     Hem
    0.05
    Activations Density 0.000%

    No Known Activations