© 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. 54258
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific programming syntax related to psi functions

    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
    alom
    -0.07
    engo
    -0.06
    gest
    -0.06
    loh
    -0.06
    iser
    -0.06
    -transitional
    -0.06
    ideographic
    -0.06
    çĦ¶
    -0.06
    /div
    -0.06
    arger
    -0.06
    POSITIVE LOGITS
    endale
    0.07
    hiro
    0.07
    isl
    0.07
    Ñıг
    0.07
    ŀĭ
    0.06
    icha
    0.06
    IRT
    0.06
    _clk
    0.06
    wand
    0.06
    zig
    0.06
    Activations Density 0.005%

    No Known Activations