© 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. 9-LLAMASCOPE-RES-131K
    11. 95839
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "going the extra mile."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    utow
    -0.07
    afone
    -0.06
    raph
    -0.06
    apult
    -0.06
    tk
    -0.06
    ufs
    -0.06
     Noel
    -0.06
    ilk
    -0.06
    uegos
    -0.06
    indir
    -0.06
    POSITIVE LOGITS
    orex
    0.07
    /cms
    0.07
    ESA
    0.07
    нез
    0.07
    ulur
    0.07
    obec
    0.07
    increments
    0.07
    кÑĢаÑĹ
    0.06
    ιδ
    0.06
    obe
    0.06
    Activations Density 0.009%

    No Known Activations