© 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. 91822
    Prev
    Next
    INDEX
    Explanations

    descriptions of vehicle handling characteristics

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    abis
    -0.08
     fod
    -0.07
    chet
    -0.07
    _compat
    -0.07
    adla
    -0.07
    emez
    -0.07
    ncmp
    -0.07
    agua
    -0.07
    ereum
    -0.07
    spm
    -0.07
    POSITIVE LOGITS
    556
    0.06
    ued
    0.06
     Tay
    0.06
     pedestrian
    0.06
     handling
    0.06
     exchanges
    0.06
     lateral
    0.05
     stiffness
    0.05
     thickness
    0.05
    hal
    0.05
    Activations Density 0.011%

    No Known Activations