© 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. 119672
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly the comma

    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
    eyer
    -0.06
    ynes
    -0.06
    udget
    -0.06
     pog
    -0.06
    fst
    -0.06
     DISCLAIMER
    -0.06
    ingen
    -0.06
    ï¿¥
    -0.05
    λα
    -0.05
    iano
    -0.05
    POSITIVE LOGITS
    erdale
    0.07
    onaut
    0.06
    .Microsoft
    0.06
     rast
    0.06
    лад
    0.06
    uyá»ĥn
    0.06
    /Foundation
    0.06
    iel
    0.06
    .TabStop
    0.06
    Č↵
    0.06
    Activations Density 0.000%

    No Known Activations