© 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. 121215
    Prev
    Next
    INDEX
    Explanations

    content related to polling and community engagement

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

    Punctuation and phrases that signal the end of content sections or invite user interaction in blog posts, forums, and interactive online content.

    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
    ombok
    -0.07
    ociety
    -0.06
    isy
    -0.06
    بت
    -0.06
     Whereas
    -0.06
    uard
    -0.06
    oth
    -0.06
     Pok
    -0.05
    lı
    -0.05
     Schw
    -0.05
    POSITIVE LOGITS
    istrovstvÃŃ
    0.08
     بشر
    0.07
    .postMessage
    0.07
    usement
    0.07
    zier
    0.07
    -------------</
    0.07
    ãĤ¹ãĥ¬
    0.07
     deadline
    0.07
     luder
    0.07
    _attachments
    0.07
    Activations Density 0.026%

    No Known Activations