© 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. 17-LLAMASCOPE-RES-131K
    11. 104326
    Prev
    Next
    INDEX
    Explanations

    structured data representing the state and output of a programming component, particularly in a JavaScript context

    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
    UPPORTED
    -0.07
    PEnd
    -0.07
     ydk
    -0.07
    GLOSS
    -0.07
    .createComponent
    -0.06
    pie
    -0.06
     stripslashes
    -0.06
    kate
    -0.06
    æĪIJ
    -0.06
     Ñģеб
    -0.06
    POSITIVE LOGITS
    çıį
    0.07
    uelles
    0.07
    ila
    0.07
    uff
    0.07
    980
    0.06
     hend
    0.06
    iti
    0.06
     zby
    0.06
    eting
    0.06
    inou
    0.06
    Activations Density 0.004%

    No Known Activations