© 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. 468
    Prev
    Next
    INDEX
    Explanations

    specific geographical and contextual references related to events or entities

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

    Special characters and formatting syntax in technical/mathematical notation, often part of command structures or variable names in code or equations.

    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
    .isSuccess
    -0.07
     Maz
    -0.07
    /body
    -0.07
    emain
    -0.07
    .mi
    -0.06
    obao
    -0.06
    ÑĢей
    -0.06
     noqa
    -0.06
    лÑıн
    -0.06
    кÑĥÑĢ
    -0.06
    POSITIVE LOGITS
    794
    0.07
    561
    0.06
    315
    0.06
    Tier
    0.06
    vanished
    0.06
    uisine
    0.06
    es
    0.06
    ÏĢον
    0.06
     Dish
    0.06
     verdienen
    0.05
    Activations Density 0.054%

    No Known Activations