© 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. 87500
    Prev
    Next
    INDEX
    Explanations

    grocery and food-related terms

    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
    ensch
    -0.07
    assage
    -0.07
    essages
    -0.07
    indow
    -0.07
     Kürt
    -0.06
    ãĤ¯ãĥĪ
    -0.06
    Χ
    -0.06
     инÑĦоÑĢма
    -0.06
    beck
    -0.06
    ìĥ
    -0.06
    POSITIVE LOGITS
    ¢åįķ
    0.06
     atmosphere
    0.06
    PostExecute
    0.06
    Calibri
    0.06
    @Spring
    0.06
    vÄĽÅĻ
    0.06
    /GPL
    0.06
    (strict
    0.06
     Mej
    0.06
    rimp
    0.06
    Activations Density 0.016%

    No Known Activations