© 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 EvalsExportsAPI 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. 3625
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to welding and machinery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Connecting phrases and contextual modifiers in technical or informational text that indicate relationships, options, or specifications.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    outu
    -0.06
     ingredients
    -0.06
     elements
    -0.06
     Ingredients
    -0.06
    elements
    -0.06
    -elements
    -0.06
    ίν
    -0.06
     ÙĪÛĮÚ©ÛĮ
    -0.06
    /browse
    -0.06
    κή
    -0.06
    POSITIVE LOGITS
     either
    0.25
     EITHER
    0.22
    either
    0.22
     Either
    0.21
    Either
    0.20
     options
    0.18
     Options
    0.16
    options
    0.15
    Options
    0.14
     choices
    0.14
    Activations Density 0.215%

    No Known Activations