© 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. 54684
    Prev
    Next
    INDEX
    Explanations

    words associated with providing food and beverages at events

    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
    ched
    -0.10
    CHED
    -0.08
    stadt
    -0.08
    adin
    -0.07
    argout
    -0.07
    redo
    -0.07
    аном
    -0.07
    Schedulers
    -0.07
    Cancelable
    -0.06
    anova
    -0.06
    POSITIVE LOGITS
    ments
    0.09
    als
    0.08
    ment
    0.08
    ingly
    0.07
    able
    0.07
    ively
    0.07
    actory
    0.07
    MENT
    0.06
    781
    0.06
    iation
    0.06
    Activations Density 0.002%

    No Known Activations