© 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. 59125
    Prev
    Next
    INDEX
    Explanations

    references to financial institutions or transactions

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

    Date markers, location identifiers, and transitional tokens that appear at content boundaries or section breaks in formatted text.

    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
     latter
    -0.08
    asz
    -0.07
    AWN
    -0.07
    omor
    -0.07
    phans
    -0.07
    pline
    -0.07
    ossip
    -0.07
    (er
    -0.07
    rol
    -0.07
    ADE
    -0.07
    POSITIVE LOGITS
    odore
    0.15
    adays
    0.14
    atre
    0.13
    etheless
    0.12
    greSQL
    0.11
    atomy
    0.10
    ÑįÑĤомÑĥ
    0.10
    quarters
    0.08
    gether
    0.08
    кÑĢаÑĹн
    0.08
    Activations Density 0.242%

    No Known Activations