© 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. 61563
    Prev
    Next
    INDEX
    Explanations

    references to specific places or organizations

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

    Section titles or headings that appear at content boundaries in structured documents like listings, catalogs, or directories.

    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
    ourg
    -0.07
    halb
    -0.07
     otherwise
    -0.06
    apiro
    -0.06
    бÑĢа
    -0.06
    .uni
    -0.06
    Liked
    -0.06
    วล
    -0.06
     accordingly
    -0.06
     etc
    -0.06
    POSITIVE LOGITS
    ↵↵
    0.07
    kır
    0.07
    plat
    0.06
     âĸ³
    0.06
    aka
    0.06
     volunteered
    0.06
    .bmp
    0.06
    arb
    0.06
    .TODO
    0.06
    æľį
    0.06
    Activations Density 0.005%

    No Known Activations