© 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. 41590
    Prev
    Next
    INDEX
    Explanations

    specific food items and their preparation methods

    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
     individual
    -0.06
     Woods
    -0.05
     style
    -0.05
    /release
    -0.05
    -local
    -0.05
     &
    -0.05
    909
    -0.05
    stand
    -0.05
     Wass
    -0.05
    ing
    -0.05
    POSITIVE LOGITS
    TRIES
    0.10
    aceous
    0.10
    -rich
    0.08
    -dominated
    0.08
    -based
    0.08
    -lined
    0.08
    -grey
    0.08
    /apple
    0.08
     içeren
    0.08
    jeta
    0.08
    Activations Density 0.015%

    No Known Activations