© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98707
    Prev
    Next
    INDEX
    Explanations

    references to dictionaries or encyclopedic sources

    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
    batim
    -0.06
    lap
    -0.05
    ef
    -0.05
    hoe
    -0.05
    hel
    -0.05
    eger
    -0.05
     kir
    -0.05
     ins
    -0.05
    TY
    -0.05
     oven
    -0.05
    POSITIVE LOGITS
    ãĤ¹ãĤ¯
    0.07
    ÏĦεÏħ
    0.07
    naire
    0.07
    ENTRY
    0.07
     Entry
    0.07
    Entry
    0.07
    setter
    0.07
     mys
    0.07
    .dex
    0.07
    едж
    0.06
    Activations Density 0.009%

    No Known Activations