© 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. 72358
    Prev
    Next
    INDEX
    Explanations

    references to religious or spiritual themes and duties

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

    Bibliographic and technical information in geological map citations, particularly publication years, scale measurements, author names, and reference numbers, along with occasional programming terms in code snippets.

    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
    rei
    -0.06
    arend
    -0.06
    ori
    -0.06
    edin
    -0.06
    .KeyCode
    -0.06
     (_.
    -0.06
    .btnClose
    -0.06
    up
    -0.06
    æŃ
    -0.06
    vey
    -0.05
    POSITIVE LOGITS
    .
    0.11
    .).↵↵
    0.08
    .).
    0.07
    .);↵
    0.07
    iaux
    0.07
    rud
    0.07
    .à¸ŀ
    0.07
    .dll
    0.07
    .:.
    0.07
    .ï¼ı
    0.07
    Activations Density 0.361%

    No Known Activations