© 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. 5987
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific models and measurements in astrophysics

    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
    efon
    -0.06
    Æ
    -0.06
     exhaustive
    -0.06
    га
    -0.06
    èį
    -0.05
     hung
    -0.05
    Auto
    -0.05
    buz
    -0.05
     Marine
    -0.05
     Auto
    -0.05
    POSITIVE LOGITS
     conv
    0.08
    \grid
    0.08
    /stream
    0.08
    dzi
    0.07
    bulan
    0.07
     transports
    0.07
    缤
    0.07
    asley
    0.07
    ibel
    0.07
    .disk
    0.07
    Activations Density 0.018%

    No Known Activations