© 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. 56502
    Prev
    Next
    INDEX
    Explanations

    references to qualities and specifications of materials in production or retail contexts

    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
     pies
    -0.07
    ombres
    -0.07
    niÄį
    -0.06
    reten
    -0.06
    ony
    -0.06
    agne
    -0.06
    ziej
    -0.06
     eser
    -0.06
    chein
    -0.06
    zet
    -0.06
    POSITIVE LOGITS
     materials
    0.14
     ingredients
    0.13
    materials
    0.13
    æĿIJæĸĻ
    0.11
     Materials
    0.11
    ingredients
    0.11
     ingredient
    0.10
     supplies
    0.10
    Materials
    0.10
     Ingredients
    0.09
    Activations Density 0.063%

    No Known Activations