© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 41409
    Prev
    Next
    INDEX
    Explanations

    terminology related to weight measurement and analysis

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    اÙģت
    -0.06
    udd
    -0.06
     Jer
    -0.06
    aut
    -0.06
    ear
    -0.06
    çĽĸ
    -0.06
    reib
    -0.06
    Col
    -0.06
    ayo
    -0.06
    asts
    -0.06
    POSITIVE LOGITS
     weight
    0.09
     weigh
    0.08
     weekly
    0.07
     Weight
    0.07
     progress
    0.07
    .getvalue
    0.07
    -week
    0.07
     measurement
    0.07
    tracker
    0.07
     measurements
    0.06
    Activations Density 0.015%

    No Known Activations