© 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 EvalsExportsinterp-engineNEWAPI 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. 89437
    Prev
    Next
    INDEX
    Explanations

    technical terms and nomenclature related to genetic and particle physics

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

    Specialized notation used as identifiers or variables in technical contexts such as mathematics, programming, or scientific nomenclature that typically appear within equations, function definitions, or code references.

    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
    åĬ
    -0.08
     erotische
    -0.07
    /loose
    -0.07
     prostitut
    -0.07
    ripe
    -0.07
    /stretch
    -0.07
    ãģ¡ãģ¯
    -0.07
    nst
    -0.07
    AYER
    -0.07
    inel
    -0.06
    POSITIVE LOGITS
    noinspection
    0.07
    ourt
    0.06
    ẽ
    0.06
    aml
    0.06
    ennis
    0.06
    orem
    0.06
    006
    0.05
    volution
    0.05
    riz
    0.05
    connexion
    0.05
    Activations Density 0.011%

    No Known Activations