© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 96218
    Prev
    Next
    INDEX
    Explanations

    comments or notes in a code or document

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ------------------------------------------------
    -0.08
    é¼
    -0.07
    --------------------------------------------------------------------------------
    -0.07
    ----------------------------------------------------------------
    -0.07
    ellite
    -0.06
    odi
    -0.06
     wid
    -0.06
    ================================================================
    -0.06
    ellery
    -0.06
    ////////////////////////////////
    -0.06
    POSITIVE LOGITS
    ä¸Ķ
    0.09
    <![
    0.08
    DTD
    0.07
    iswa
    0.06
    ι
    0.06
    zing
    0.06
     NOP
    0.06
    away
    0.06
    nds
    0.06
    atic
    0.06
    Activations Density 0.023%

    No Known Activations