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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 103320
    Prev
    Next
    INDEX
    Explanations

    classifications and categorizations of substances or entities

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

    Classification markers, category designations, and formatting elements in structured data that indicate types, groups, or hierarchical relationships.

    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
    ague
    -0.08
    ãĤ¤ãĤº
    -0.07
    ãĥªãĥ¼ãĤº
    -0.07
    ?url
    -0.06
    abis
    -0.06
     Barnett
    -0.06
     precinct
    -0.06
    ä¸Ī
    -0.06
    agues
    -0.06
     Reeves
    -0.06
    POSITIVE LOGITS
     category
    0.09
    ype
    0.08
     kategor
    0.08
     mixed
    0.08
     type
    0.08
     Mixed
    0.08
     Category
    0.08
     Type
    0.07
    à¸Ľà¸£à¸°à¹Ģà¸łà¸Ĺ
    0.07
    ç±»åŀĭ
    0.07
    Activations Density 0.157%

    No Known Activations