© 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. 17-LLAMASCOPE-RES-131K
    6. 75819
    Prev
    Next
    INDEX
    Explanations

    variables and functions related to file handling in programming code

    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
    DAL
    -0.06
    -v
    -0.06
    dal
    -0.06
    Dal
    -0.06
     Ses
    -0.06
     Gra
    -0.06
     Basic
    -0.05
    (url
    -0.05
     Fur
    -0.05
    graf
    -0.05
    POSITIVE LOGITS
    Naming
    0.10
    åIJįåīį
    0.09
     naming
    0.09
    lename
    0.08
     file
    0.08
     Naming
    0.08
    Ending
    0.08
     files
    0.08
    .Atomic
    0.08
    erot
    0.08
    Activations Density 0.045%

    No Known Activations