© 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. 15-LLAMASCOPE-RES-131K
    11. 88642
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "avant-garde"

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

    Common syllables or word parts that frequently appear across different languages, particularly in academic, cultural, or technical contexts, with "avant" notably appearing in discussions of artistic innovation.

    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
    ting
    -0.10
    ãģ°
    -0.09
    bers
    -0.08
    uting
    -0.07
    dna
    -0.07
    flo
    -0.07
    ged
    -0.07
    rint
    -0.07
    oka
    -0.06
    bing
    -0.06
    POSITIVE LOGITS
    eur
    0.09
    eb
    0.08
    tir
    0.07
    t
    0.07
    Äĥm
    0.07
    eu
    0.07
    ech
    0.07
    º
    0.07
    eed
    0.07
    ÃŃÅĻ
    0.07
    Activations Density 0.063%

    No Known Activations