© 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 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. 16383
    Prev
    Next
    INDEX
    Explanations

    phrases related to inclusion and file path references in technical contexts

    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
    awi
    -0.08
    abad
    -0.07
     Issue
    -0.07
    _Tis
    -0.07
    UGIN
    -0.07
    Å¡et
    -0.06
    ongan
    -0.06
     Challenger
    -0.06
    alker
    -0.06
    oui
    -0.06
    POSITIVE LOGITS
     include
    0.07
    inclu
    0.07
    ardu
    0.06
     Larson
    0.06
    aan
    0.06
     hook
    0.06
    hek
    0.06
     includ
    0.06
     consent
    0.06
     includes
    0.06
    Activations Density 0.006%

    No Known Activations