© 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. 85728
    Prev
    Next
    INDEX
    Explanations

    legislative actions and terms related to bills or resolutions

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

    The token "description" followed by symbols or text that indicates status or categorization in technical documentation, often appearing in code comments, API references, or legislative tracking systems.

    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
     dok
    -0.06
    iminal
    -0.06
    βα
    -0.06
     Falk
    -0.06
     slee
    -0.05
     exit
    -0.05
    9
    -0.05
    1
    -0.05
     tips
    -0.05
    ervo
    -0.05
    POSITIVE LOGITS
     description
    0.13
     Description
    0.12
    description
    0.11
    .description
    0.11
    _description
    0.11
    DESCRIPTION
    0.11
    Description
    0.10
     getDescription
    0.10
    -description
    0.10
    .setDescription
    0.10
    Activations Density 0.028%

    No Known Activations