© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 127175
    Prev
    Next
    INDEX
    Explanations

    references to plants and their characteristics in design contexts

    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
    599
    -0.07
    udd
    -0.06
    /us
    -0.06
    vd
    -0.06
     Stall
    -0.06
    amer
    -0.05
     luk
    -0.05
     tep
    -0.05
     Field
    -0.05
    vang
    -0.05
    POSITIVE LOGITS
     spontaneously
    0.07
    activex
    0.07
    _coverage
    0.07
    ảnh
    0.07
    serter
    0.07
     Coverage
    0.07
    дан
    0.07
    meyi
    0.07
    rol
    0.07
    ả
    0.06
    Activations Density 0.015%

    No Known Activations