© 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. 30540
    Prev
    Next
    INDEX
    Explanations

    descriptions of food preparation and cooking techniques

    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
    uger
    -0.06
     attempt
    -0.06
    tright
    -0.06
    deen
    -0.06
    attempt
    -0.06
    cano
    -0.06
    å¥Ĺ
    -0.06
    acle
    -0.06
    оÑĢи
    -0.06
    CES
    -0.06
    POSITIVE LOGITS
     Podle
    0.06
    iny
    0.06
    urity
    0.06
    ylie
    0.06
    ä¸Ī
    0.06
    .GetProperty
    0.06
    istine
    0.06
    rawing
    0.06
    кÑĥÑģ
    0.06
    ollectors
    0.06
    Activations Density 0.040%

    No Known Activations