© 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. 27435
    Prev
    Next
    INDEX
    Explanations

    titles and roles associated with individuals in academic and professional contexts

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

    Professional titles or roles designating a person's official position or function within an organization, publication, or project.

    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
    opus
    -0.07
    anka
    -0.07
    indy
    -0.07
    ech
    -0.07
    anter
    -0.06
    ard
    -0.06
    erior
    -0.06
    askets
    -0.06
    eer
    -0.06
    artic
    -0.06
    POSITIVE LOGITS
    (s
    0.08
    :
    0.07
    ï¸
    0.06
    ÑĮÑı
    0.06
     ØŃسب
    0.06
    /editor
    0.06
    plib
    0.06
     spo
    0.06
    >');↵↵
    0.06
    chwitz
    0.06
    Activations Density 0.027%

    No Known Activations