© 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. 58619
    Prev
    Next
    INDEX
    Explanations

    phrases indicating medical or health-related concepts

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

    Section headers that introduce new topical content in articles or reports, appearing at content transition points.

    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
    окÑĢема
    -0.08
     latter
    -0.07
    ĥĿ
    -0.07
    inu
    -0.07
    ehr
    -0.06
    visor
    -0.06
    دÛĮگر
    -0.06
    åĨµ
    -0.06
    .googlecode
    -0.06
    dap
    -0.06
    POSITIVE LOGITS
    0.07
     ↵↵
    0.07
    ÑĢаÑģÑĤа
    0.07
    beck
    0.06
     
    0.06
    Since
    0.06
    .onCreate
    0.06
     As
    0.06
    .Messaging
    0.06
    koli
    0.06
    Activations Density 0.034%

    No Known Activations