© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76039
    Prev
    Next
    INDEX
    Explanations

    attributes related to graphical icons and their emotional expressions

    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
    undra
    -0.07
    нÑĸм
    -0.06
    [".
    -0.06
    licken
    -0.06
     Ñģамого
    -0.06
    .navigator
    -0.06
    owitz
    -0.06
    еÑģи
    -0.06
    /misc
    -0.06
    повÑĸд
    -0.06
    POSITIVE LOGITS
     .
    0.06
    012
    0.06
    rex
    0.06
    uais
    0.06
     Hanna
    0.06
    udio
    0.06
     McM
    0.06
    ¦
    0.06
    (disposing
    0.06
     tiger
    0.06
    Activations Density 0.052%

    No Known Activations