© 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. 116349
    Prev
    Next
    INDEX
    Explanations

    numerical information related to legal services and attorney experience

    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
    иÑĤи
    -0.06
    ssp
    -0.06
    stance
    -0.06
    emachine
    -0.06
    ubs
    -0.06
    auc
    -0.06
    uru
    -0.06
    jure
    -0.06
     충
    -0.06
    itas
    -0.06
    POSITIVE LOGITS
    phin
    0.07
    SEA
    0.07
    cone
    0.07
    erdale
    0.06
    /GPL
    0.06
     infect
    0.06
    _BS
    0.06
    entai
    0.06
    sea
    0.06
    ÃĶ
    0.06
    Activations Density 0.001%

    No Known Activations