© 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. 99263
    Prev
    Next
    INDEX
    Explanations

    references to racing or competitive events

    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
    /arch
    -0.07
    ipt
    -0.07
    .accel
    -0.07
    ipel
    -0.06
     Thur
    -0.06
    ansson
    -0.06
    ÐĽÐ¬
    -0.06
    ìĩ
    -0.06
    obao
    -0.06
    éĢīæĭ
    -0.06
    POSITIVE LOGITS
    461
    0.07
    è
    0.06
    orsk
    0.06
    iment
    0.06
    IMUM
    0.06
    457
    0.06
    atore
    0.06
     اÙĦدر
    0.06
    roads
    0.06
    ISTRY
    0.06
    Activations Density 0.001%

    No Known Activations