© 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 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. 16403
    Prev
    Next
    INDEX
    Explanations

    programming-related operations and control flow constructs

    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
    _tac
    -0.07
    å®ĩ
    -0.07
    antz
    -0.06
    afd
    -0.06
    CallBack
    -0.06
    adge
    -0.06
    æĭ¿
    -0.06
    ades
    -0.06
     mü
    -0.06
    _indx
    -0.06
    POSITIVE LOGITS
    ध
    0.06
    äºķ
    0.06
    ypi
    0.06
     builtin
    0.06
     Contents
    0.06
    anine
    0.06
     cmdline
    0.06
     Mayo
    0.06
    Fmt
    0.06
     Wire
    0.06
    Activations Density 0.988%

    No Known Activations