© 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. 63293
    Prev
    Next
    INDEX
    Explanations

    punctuation marks or symbols in text

    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
     Ones
    -0.08
    çļĦæĺ¯
    -0.07
    quot
    -0.06
    eniable
    -0.06
    ersh
    -0.06
     Bro
    -0.06
    incare
    -0.06
    hton
    -0.06
    uct
    -0.06
    emb
    -0.06
    POSITIVE LOGITS
     which
    0.12
    which
    0.10
     vá»ijn
    0.09
    ä¸Ģç§į
    0.08
     WHICH
    0.08
     wich
    0.08
    Which
    0.07
     Which
    0.07
    FileSync
    0.07
    stadt
    0.06
    Activations Density 0.035%

    No Known Activations