© 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. 15-LLAMASCOPE-RES-131K
    11. 87129
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword "public" in the context of code

    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
    960
    -0.06
    iji
    -0.06
    is
    -0.06
    cház
    -0.06
     Kou
    -0.06
    882
    -0.06
    oll
    -0.06
    idis
    -0.06
     tim
    -0.06
    elier
    -0.06
    POSITIVE LOGITS
    SetActive
    0.07
    AEA
    0.07
    tuk
    0.07
    /LICENSE
    0.07
    νÏī
    0.06
    \Collections
    0.06
    θή
    0.06
    SqlParameter
    0.06
    apot
    0.06
     огÑĢа
    0.06
    Activations Density 0.003%

    No Known Activations