© 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. 2083
    Prev
    Next
    INDEX
    Explanations

    phrases related to creativity and unique expressions

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

    Common conversational phrases, idioms, and figures of speech that add informal tone to the text, often appearing before or within quotations.

    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
     Bilg
    -0.08
     meÅŁ
    -0.08
    .peer
    -0.07
    iá»ģn
    -0.07
    #ad
    -0.07
    Carrier
    -0.07
    ÑijÑĤ
    -0.07
    меÑĩ
    -0.07
     GENERIC
    -0.07
    wargs
    -0.07
    POSITIVE LOGITS
    ·
    0.07
     McCartney
    0.06
     Levi
    0.06
     '
    0.06
    ars
    0.05
    (e
    0.05
    915
    0.05
     enlight
    0.05
     MD
    0.05
     (
    0.05
    Activations Density 0.126%

    No Known Activations