© 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. 130448
    Prev
    Next
    INDEX
    Explanations

    references to brushing or related grooming actions

    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
    éł¼
    -0.07
    ansa
    -0.07
    ummings
    -0.07
    ymes
    -0.07
    볨
    -0.07
    reeNode
    -0.07
    eed
    -0.07
    itud
    -0.07
    dropout
    -0.07
     imageSize
    -0.06
    POSITIVE LOGITS
     aside
    0.09
    aside
    0.07
     brush
    0.07
    aru
    0.07
    brush
    0.06
     Aside
    0.06
     away
    0.06
     gloss
    0.06
     off
    0.06
    qui
    0.06
    Activations Density 0.004%

    No Known Activations