© 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. 94104
    Prev
    Next
    INDEX
    Explanations

    numeric values or measurements in a document

    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
    PermissionsResult
    -0.08
    UrlParser
    -0.07
    argin
    -0.07
    /stdc
    -0.07
    646
    -0.07
    esis
    -0.07
    onest
    -0.07
    \Migration
    -0.07
    iversal
    -0.07
    RuntimeObject
    -0.06
    POSITIVE LOGITS
    Äı
    0.08
    á»ı
    0.07
     tarif
    0.07
    tres
    0.07
     reife
    0.06
    .Automation
    0.06
     pek
    0.06
    ìŀIJìĿ¸
    0.06
     ATA
    0.06
    ť
    0.06
    Activations Density 0.082%

    No Known Activations