© 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. 103866
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting elements

    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
    892
    -0.08
     нада
    -0.07
    /Dk
    -0.07
    ternet
    -0.07
    ovit
    -0.06
    ần
    -0.06
    ingo
    -0.06
    ýš
    -0.06
    Ä°Y
    -0.06
    enger
    -0.06
    POSITIVE LOGITS
    ä¹Ļ
    0.06
    olls
    0.06
    grim
    0.06
    .debian
    0.06
    liches
    0.06
     Salah
    0.06
    ublic
    0.06
     (
    0.06
    (ii
    0.06
    -uppercase
    0.05
    Activations Density 0.015%

    No Known Activations