© 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. 62004
    Prev
    Next
    INDEX
    Explanations

    keywords related to food ingredients and sauces

    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
    kup
    -0.08
    shint
    -0.07
    -Ф
    -0.07
    пÑĢимеÑĢ
    -0.06
     Krish
    -0.06
    ervers
    -0.06
    CCI
    -0.06
    алÑĥ
    -0.06
    ough
    -0.06
    inth
    -0.06
    POSITIVE LOGITS
    icker
    0.08
    CLUDING
    0.06
    cludes
    0.06
    ROT
    0.06
    yla
    0.06
    ãĥ¼ãĥĪ
    0.06
     finished
    0.06
    è£
    0.06
    sg
    0.05
     Dirt
    0.05
    Activations Density 0.011%

    No Known Activations