© 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. 93965
    Prev
    Next
    INDEX
    Explanations

    instructions pertaining to cooking or baking processes

    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
    /fw
    -0.08
    ÑĪÑĥ
    -0.07
    ãĥ¼ãĤº
    -0.06
    /tos
    -0.06
    ently
    -0.06
    istrovstvÃŃ
    -0.06
     Lazar
    -0.06
    ufe
    -0.06
    боÑĤ
    -0.06
    ConverterFactory
    -0.06
    POSITIVE LOGITS
    пиÑģ
    0.07
    rollo
    0.06
     butter
    0.06
    ples
    0.06
    BCM
    0.06
     amat
    0.06
     Playground
    0.06
    EDA
    0.06
     Butter
    0.06
     roll
    0.06
    Activations Density 0.009%

    No Known Activations