© 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 EvalsExportsAPI 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. 106684
    Prev
    Next
    INDEX
    Explanations

    terms related to competition or achievement

    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
    ëŀ
    -0.07
    nelle
    -0.07
    abo
    -0.07
    ÑĢап
    -0.07
    รà¸Ķ
    -0.07
    uplicates
    -0.06
     lekker
    -0.06
    ivol
    -0.06
    èIJ½
    -0.06
    æĸĻ
    -0.06
    POSITIVE LOGITS
    airy
    0.06
    untas
    0.06
    enen
    0.06
    æľī人
    0.06
    tridge
    0.06
    ëĶĶìĭľ
    0.06
     Brom
    0.06
    inton
    0.06
    FFFFFFFF
    0.06
    eru
    0.06
    Activations Density 0.000%

    No Known Activations