© 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. 69131
    Prev
    Next
    INDEX
    Explanations

    terms related to numerical values, particularly focusing on positivity, negativity, and the classification of numbers

    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
    по
    -0.06
    //{{
    -0.06
    rer
    -0.06
     klu
    -0.06
    RFC
    -0.06
     sche
    -0.06
    urette
    -0.06
    ivor
    -0.06
    _IA
    -0.06
    ůst
    -0.05
    POSITIVE LOGITS
    /n
    0.07
    IntegerField
    0.07
    amm
    0.07
    rades
    0.07
    lán
    0.07
    igs
    0.07
    /null
    0.07
    arrant
    0.07
    asket
    0.07
     Jah
    0.07
    Activations Density 0.034%

    No Known Activations