© 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. 9-LLAMASCOPE-RES-131K
    11. 93952
    Prev
    Next
    INDEX
    Explanations

    comparisons of significance or attractiveness regarding people or things

    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
    oston
    -0.06
    оÑģÑĮ
    -0.06
    ivalent
    -0.06
    ordes
    -0.06
     mex
    -0.06
    thes
    -0.06
    YTE
    -0.06
    inue
    -0.06
    orde
    -0.06
    ect
    -0.06
    POSITIVE LOGITS
    tü
    0.08
    tür
    0.07
    ISK
    0.07
     æĬķ稿
    0.06
    abcdefghijklmnop
    0.06
    geber
    0.06
    isk
    0.06
    vio
    0.06
    afi
    0.06
    ucene
    0.06
    Activations Density 0.007%

    No Known Activations