© 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. 3582
    Prev
    Next
    INDEX
    Explanations

    mentions of clothing, specifically dresses and formal attire

    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
    feito
    -0.07
    erap
    -0.07
    psc
    -0.07
    ocard
    -0.06
    /MIT
    -0.06
    ypse
    -0.06
    hip
    -0.06
    ritt
    -0.06
    olk
    -0.06
     rel
    -0.06
    POSITIVE LOGITS
     worn
    0.08
    MediaType
    0.07
    cratch
    0.07
    èįī
    0.07
    etwork
    0.07
    еÑĤом
    0.07
     bottoms
    0.06
    ETYPE
    0.06
    otel
    0.06
    ÃŃky
    0.06
    Activations Density 0.027%

    No Known Activations