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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 128705
    Prev
    Next
    INDEX
    Explanations

    numerical data and quantities related to various topics

    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
    ardi
    -0.07
     sice
    -0.07
    owski
    -0.06
    ÑĢÑıдÑĥ
    -0.06
     ابتدا
    -0.06
    otti
    -0.06
     wäh
    -0.06
     ziy
    -0.06
    yar
    -0.06
     cuk
    -0.06
    POSITIVE LOGITS
     equally
    0.09
    ãģĿãģĹãģ¦
    0.08
    .TryParse
    0.08
    /OR
    0.07
    /or
    0.07
     ê·¸ë¦¬ê³ł
    0.07
    reation
    0.07
     countless
    0.06
    endon
    0.06
    jos
    0.06
    Activations Density 0.060%

    No Known Activations