© 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. 31199
    Prev
    Next
    INDEX
    Explanations

    time durations related to cooking or baking instructions

    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
    æĢ
    -0.07
     ISS
    -0.06
     bot
    -0.06
    obot
    -0.06
    airo
    -0.06
    angu
    -0.06
     aug
    -0.06
    allen
    -0.06
    ount
    -0.05
     Col
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.09
    processable
    0.07
    Signature
    0.07
    *@
    0.07
    оÑĢод
    0.07
    _NOTIFY
    0.06
    .getElementsByName
    0.06
    Ñĥнд
    0.06
    cased
    0.06
     Affero
    0.06
    Activations Density 0.007%

    No Known Activations