© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96288
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to functions and data structure assignments

    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
    OSH
    -0.07
    erner
    -0.07
    osh
    -0.06
    cplusplus
    -0.06
    ALSE
    -0.06
     lyon
    -0.06
    itu
    -0.06
    oric
    -0.06
     Millions
    -0.06
    GU
    -0.05
    POSITIVE LOGITS
    cant
    0.07
    again
    0.07
    asury
    0.06
    untime
    0.06
    okens
    0.06
    bpp
    0.06
     zg
    0.06
     /*!<
    0.06
    igli
    0.06
    utoff
    0.06
    Activations Density 0.206%

    No Known Activations