© 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. 107579
    Prev
    Next
    INDEX
    Explanations

    details related to cooking instructions and food presentation

    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
    inke
    -0.07
    aho
    -0.06
    eki
    -0.06
    whereIn
    -0.06
    ccoli
    -0.06
    ohana
    -0.06
    ker
    -0.06
     zev
    -0.06
    åłĤ
    -0.06
     Nachricht
    -0.06
    POSITIVE LOGITS
    hen
    0.07
     íĴ
    0.06
    .lex
    0.06
    Spread
    0.06
     towards
    0.06
    ãĥ©ãĥ³ãĥī
    0.06
     Tow
    0.06
    aled
    0.06
     Huffman
    0.06
    ToDevice
    0.06
    Activations Density 0.014%

    No Known Activations