© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 27882
    Prev
    Next
    INDEX
    Explanations

    language related to food, recipes, and culinary experiences

    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
     fasc
    -0.07
     Fasc
    -0.06
    heim
    -0.06
     Sig
    -0.06
    ongan
    -0.06
     contrary
    -0.06
    ertino
    -0.06
    anggal
    -0.06
    ÏģοÏħ
    -0.06
    guess
    -0.06
    POSITIVE LOGITS
    riba
    0.07
    735
    0.07
     Rim
    0.06
    iete
    0.06
    ackson
    0.06
    oli
    0.06
     seriously
    0.06
    efe
    0.06
    ichel
    0.06
    eness
    0.06
    Activations Density 0.017%

    No Known Activations