© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42497
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and references related to genetics and molecular biology

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

    Scientific and technical terminology appearing in specialized contexts, including gene names (MST3N), food items (wurst), structural elements (crust), and telecommunications terms.

    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
    er
    -0.09
    has
    -0.08
    ãģĦãĤĭ
    -0.08
    erb
    -0.08
    thon
    -0.08
    kest
    -0.08
    aison
    -0.07
    trust
    -0.07
    erence
    -0.07
    erse
    -0.07
    POSITIVE LOGITS
    itution
    0.09
    andard
    0.09
    ive
    0.09
    eners
    0.09
    ech
    0.09
    yr
    0.09
    ebin
    0.09
    inction
    0.08
    tir
    0.08
     gắng
    0.08
    Activations Density 0.087%

    No Known Activations