© 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. 27087
    Prev
    Next
    INDEX
    Explanations

    complicated agreements or clauses regarding stipulations and conditions

    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
    istry
    -0.07
    indsight
    -0.07
    eres
    -0.06
    IVES
    -0.06
    inez
    -0.06
    ucursal
    -0.06
    zac
    -0.06
    erp
    -0.06
    eras
    -0.06
    ific
    -0.06
    POSITIVE LOGITS
    loi
    0.08
    aldi
    0.08
    PLE
    0.07
    olo
    0.07
    urn
    0.07
    gle
    0.07
     Bri
    0.07
    ulus
    0.07
    tember
    0.06
    sville
    0.06
    Activations Density 0.002%

    No Known Activations