© 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. 80810
    Prev
    Next
    INDEX
    Explanations

    references to "rear" and "rear seat" configurations in vehicles

    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
    ots
    -0.07
    екаÑĢ
    -0.07
    holding
    -0.07
    ellen
    -0.07
    etz
    -0.07
    æł·çļĦ
    -0.06
    ellan
    -0.06
    kır
    -0.06
    å«
    -0.06
    etta
    -0.06
    POSITIVE LOGITS
    /front
    0.11
    /back
    0.11
    ward
    0.10
    most
    0.10
    -most
    0.09
    wards
    0.09
    (back
    0.09
    ities
    0.08
    WARDS
    0.07
    -facing
    0.07
    Activations Density 0.005%

    No Known Activations