© 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. 17-LLAMASCOPE-RES-131K
    11. 105795
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their connections to various fields, particularly in academia and the arts

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

    Names, professional titles, organizational affiliations, and location identifiers in structured professional or academic listings.

    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
    asca
    -0.08
    eof
    -0.07
    _
    -0.06
     infer
    -0.06
    avis
    -0.06
    redd
    -0.06
    redo
    -0.06
    icas
    -0.06
    estate
    -0.06
    camp
    -0.06
    POSITIVE LOGITS
    /autoload
    0.07
    638
    0.07
    stddef
    0.06
    ]</
    0.06
    olo
    0.06
    ãģķãģ¾
    0.06
    ãĥŃãĥ¼
    0.06
    SupportedContent
    0.06
     ê°¤ë¡ľê·¸ë¡ľ
    0.06
     pinterest
    0.06
    Activations Density 0.108%

    No Known Activations