© 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. 41341
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or intent

    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
    æŃ³
    -0.09
    /slick
    -0.07
     Scores
    -0.07
    uso
    -0.07
    uitka
    -0.07
    hread
    -0.06
    лÑİб
    -0.06
    iske
    -0.06
    udu
    -0.06
    ductive
    -0.06
    POSITIVE LOGITS
    y
    0.08
    çļĦè¯Ŀ
    0.07
    671
    0.06
    defer
    0.06
    riz
    0.06
    æĸĩ
    0.06
    .fe
    0.06
    Multiply
    0.06
    ale
    0.05
    kus
    0.05
    Activations Density 0.016%

    No Known Activations