© 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. 58874
    Prev
    Next
    INDEX
    Explanations

    references to web development and scripting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Software library, framework, or technology project names appearing in code, URLs, repository paths, and documentation.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    plr
    -0.07
    merce
    -0.07
    amar
    -0.07
    edis
    -0.06
    erval
    -0.06
    ARA
    -0.06
    pline
    -0.06
    αÏģά
    -0.06
     Arrow
    -0.06
    à¹Ĥย
    -0.06
    POSITIVE LOGITS
    åĿĽ
    0.08
    -fontawesome
    0.07
    ;amp
    0.07
    AU
    0.06
    831
    0.06
    AUSE
    0.06
    endon
    0.06
    íħĶ
    0.06
    립
    0.06
    porno
    0.06
    Activations Density 0.032%

    No Known Activations