© 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. 108808
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those associated with identifiers or references in a structured format

    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
    moth
    -0.07
    ilon
    -0.07
    iran
    -0.07
    posix
    -0.07
    457
    -0.07
    lc
    -0.07
    UnderTest
    -0.06
    /animations
    -0.06
    ugi
    -0.06
    aco
    -0.06
    POSITIVE LOGITS
    rido
    0.07
     Richards
    0.07
    eger
    0.07
    -uppercase
    0.07
    Å¡ov
    0.06
    ante
    0.06
    cole
    0.06
    rå
    0.06
    à¹Īà¸Ńà¸ĩ
    0.06
    _FILL
    0.06
    Activations Density 0.010%

    No Known Activations