© 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. 14256
    Prev
    Next
    INDEX
    Explanations

    numerical values and their relationships in different contexts

    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
    oron
    -0.07
    itra
    -0.06
    otland
    -0.06
    duck
    -0.06
     ::↵
    -0.06
    اÛĮØ´
    -0.06
    ::/
    -0.06
    avanaugh
    -0.06
    _IA
    -0.06
     Tür
    -0.06
    POSITIVE LOGITS
     smaller
    0.14
     lesser
    0.09
     shorter
    0.09
    å°ı
    0.07
     less
    0.07
     moins
    0.07
     meno
    0.07
    aim
    0.07
     mere
    0.07
    ear
    0.06
    Activations Density 0.079%

    No Known Activations