© 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. 99017
    Prev
    Next
    INDEX
    Explanations

    terms related to contracts and negotiations

    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
    fried
    -0.07
     toll
    -0.06
    fers
    -0.06
     Dorm
    -0.06
    ninger
    -0.06
    еÑĢеÑĩ
    -0.06
     Toll
    -0.06
    getc
    -0.06
    _logical
    -0.06
     alright
    -0.06
    POSITIVE LOGITS
    afen
    0.08
    terr
    0.07
    .writeHead
    0.07
    170
    0.06
    pars
    0.06
    odon
    0.06
    лей
    0.06
    riad
    0.06
    sr
    0.06
    abilit
    0.06
    Activations Density 0.001%

    No Known Activations