© 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. 17-LLAMASCOPE-RES-131K
    11. 16878
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and functions associated with data manipulation and math operations

    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
    653
    -0.07
    siz
    -0.06
    rar
    -0.06
     sustain
    -0.06
    ãĥ¼
    -0.06
     sik
    -0.06
     دخ
    -0.06
    allis
    -0.06
     Booker
    -0.05
    íģ¼
    -0.05
    POSITIVE LOGITS
    .of
    0.08
    iyas
    0.08
    opia
    0.07
    mani
    0.07
    elpers
    0.07
    ://
    0.07
    .Of
    0.07
    .forName
    0.07
    okers
    0.06
    atoria
    0.06
    Activations Density 0.019%

    No Known Activations