© 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. 89405
    Prev
    Next
    INDEX
    Explanations

    underscores and special characters in programming or data structures

    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
    s
    -0.06
    /not
    -0.06
    es
    -0.06
    [
    -0.06
     stat
    -0.06
     v
    -0.06
     over
    -0.05
    f
    -0.05
     Stat
    -0.05
     colon
    -0.05
    POSITIVE LOGITS
    Throws
    0.07
    ettel
    0.07
    uin
    0.07
    uD
    0.07
    quine
    0.07
    ulla
    0.07
    etro
    0.07
    umd
    0.07
    /fw
    0.07
    umar
    0.07
    Activations Density 0.034%

    No Known Activations