© 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. 59997
    Prev
    Next
    INDEX
    Explanations

    references to literary awards and their winners

    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
     ley
    -0.06
    emme
    -0.06
    uilder
    -0.06
    ollar
    -0.06
    abil
    -0.06
    ãĤ¸ãĤ¢
    -0.06
    543
    -0.06
     Lod
    -0.06
    FDA
    -0.06
    plorer
    -0.05
    POSITIVE LOGITS
    ICO
    0.07
    osi
    0.07
     )"
    0.07
     Morse
    0.07
    zÄĻ
    0.06
     vinc
    0.06
     Tu
    0.06
     thiá»ĩn
    0.06
    leck
    0.06
    -deals
    0.06
    Activations Density 0.003%

    No Known Activations