© 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. 121651
    Prev
    Next
    INDEX
    Explanations

    details about automotive models and specifications

    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
    abbo
    -0.06
    .rar
    -0.06
     stip
    -0.06
    ¼åIJĪ
    -0.06
    itchens
    -0.06
    otope
    -0.06
     Damen
    -0.06
    ãĥ¼ãĥij
    -0.05
    elic
    -0.05
    orsche
    -0.05
    POSITIVE LOGITS
     models
    0.10
     lineup
    0.09
    models
    0.09
     Models
    0.09
    _models
    0.08
    (models
    0.08
     entry
    0.08
    -model
    0.08
    emodel
    0.07
     serie
    0.07
    Activations Density 0.030%

    No Known Activations