© 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. 93956
    Prev
    Next
    INDEX
    Explanations

    references to cultural events and programming in an art context

    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
    radient
    -0.08
     bát
    -0.07
    INGER
    -0.07
     principals
    -0.07
     airports
    -0.07
     jadx
    -0.07
    ìn
    -0.07
    undef
    -0.07
    oultry
    -0.07
    olini
    -0.06
    POSITIVE LOGITS
     museum
    0.07
     curator
    0.07
     programs
    0.07
     visitors
    0.07
    nz
    0.06
     muse
    0.06
     events
    0.06
     visitor
    0.06
     Kids
    0.06
     kids
    0.06
    Activations Density 0.033%

    No Known Activations