© 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. 104416
    Prev
    Next
    INDEX
    Explanations

    specific cooking or baking instructions related to dough preparation

    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
    umo
    -0.08
     entry
    -0.07
     Entry
    -0.06
    umba
    -0.06
    rana
    -0.06
     solid
    -0.06
    omba
    -0.06
    ξε
    -0.06
     sound
    -0.06
    chten
    -0.06
    POSITIVE LOGITS
     gấp
    0.06
    uat
    0.06
    ?(:
    0.06
    _ED
    0.06
    .Slf
    0.06
     plat
    0.06
    çīĩ
    0.06
     rectangle
    0.06
    .Roll
    0.06
    sheets
    0.06
    Activations Density 0.016%

    No Known Activations