© 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. 17-LLAMASCOPE-RES-131K
    11. 39990
    Prev
    Next
    INDEX
    Explanations

    specific scientific or technical concepts related to gravitational action and mathematical definitions

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

    Syntactic elements in code and mathematical notation, particularly special characters, delimiters, and identifiers that form structural components like brackets, variable names, function references, and syntax markers.

    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
    WARDED
    -0.09
    -lnd
    -0.09
    -Semit
    -0.08
    -wsj
    -0.08
    	ROM
    -0.08
    'gc
    -0.08
    apgolly
    -0.08
     mắc
    -0.08
     kred
    -0.08
    swire
    -0.08
    POSITIVE LOGITS
     âĢ¦↵
    0.09
    âĢ¦↵
    0.09
     [âĢ¦]↵
    0.07
    Ãĥ
    0.06
     ...↵
    0.06
    ...↵
    0.06
     [
    0.05
     ..↵
    0.05
    [âĢ¦
    0.05
    /buttons
    0.05
    Activations Density 12.739%

    No Known Activations