© 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. 72823
    Prev
    Next
    INDEX
    Explanations

    references to food and beverage safety regulations

    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
    icut
    -0.07
    zen
    -0.07
     fellow
    -0.07
    leh
    -0.06
    ли
    -0.06
     SLOT
    -0.06
    orestation
    -0.06
     Bare
    -0.06
     пÑĢаÑĨÑĸв
    -0.06
    ullet
    -0.06
    POSITIVE LOGITS
     growing
    0.07
    ãĥ¼ãĥł
    0.07
     sorts
    0.07
    ibel
    0.07
    egan
    0.07
    zeit
    0.06
    esper
    0.06
     kinds
    0.06
    anje
    0.06
    uldu
    0.06
    Activations Density 0.220%

    No Known Activations