© 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. 89197
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation related to properties and definitions in the context of analysis and solutions of equations

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

    Mathematical and programming syntax elements, particularly punctuation (commas, parentheses), variable subscripts, and code identifiers that structure formal expressions or define parameters.

    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
    âĢ¦.↵↵
    -0.08
    $LANG
    -0.08
    (çģ«
    -0.07
    729
    -0.07
    æ±ł
    -0.07
    $MESS
    -0.07
    кÑĥÑĤ
    -0.07
    تÙĥ
    -0.07
    (æ°´
    -0.07
    inclu
    -0.07
    POSITIVE LOGITS
    tas
    0.08
    otland
    0.07
    ady
    0.07
    ipeg
    0.06
    cheon
    0.06
    .Drawing
    0.06
    eliness
    0.06
    ascade
    0.06
    icers
    0.06
    ople
    0.06
    Activations Density 0.222%

    No Known Activations