© 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. 126592
    Prev
    Next
    INDEX
    Explanations

    descriptions of plant species and their characteristics

    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
    .IsEmpty
    -0.07
    ullen
    -0.07
    echa
    -0.07
    ìĹ
    -0.07
    Visibility
    -0.06
     Sle
    -0.06
    ertz
    -0.06
    è£ı
    -0.06
    endar
    -0.06
    ánh
    -0.06
    POSITIVE LOGITS
     throughout
    0.09
     anywhere
    0.09
     everywhere
    0.07
     in
    0.07
     Distributed
    0.07
     exclusively
    0.07
     wherever
    0.07
     across
    0.06
     around
    0.06
     somewhere
    0.06
    Activations Density 0.018%

    No Known Activations