© 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. 27905
    Prev
    Next
    INDEX
    Explanations

    references to web browsing issues related to JavaScript

    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
     Dam
    -0.07
    _INCLUDED
    -0.07
    ñana
    -0.06
    ziej
    -0.06
    _NAMESPACE
    -0.06
    aticon
    -0.06
    اس
    -0.06
     Gron
    -0.06
     Larson
    -0.06
    ycler
    -0.06
    POSITIVE LOGITS
    aren
    0.06
     Gan
    0.06
    arf
    0.06
    ijn
    0.06
    /gui
    0.06
    ัà¸į
    0.06
    ког
    0.06
    Boost
    0.06
    leep
    0.06
    nge
    0.06
    Activations Density 0.003%

    No Known Activations