© 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. 130196
    Prev
    Next
    INDEX
    Explanations

    code elements and syntax related to programming logic 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
    ogan
    -0.10
    engin
    -0.08
    apel
    -0.07
    epar
    -0.07
    ampionship
    -0.07
    chte
    -0.07
    egan
    -0.07
    auf
    -0.07
    ukan
    -0.07
    incinnati
    -0.07
    POSITIVE LOGITS
     POSSIBILITY
    0.08
     Tops
    0.07
    _keeper
    0.07
    -prev
    0.06
    ÑĤÑĢо
    0.06
    678
    0.06
     collectively
    0.06
    -caret
    0.06
    formace
    0.06
    828
    0.06
    Activations Density 0.001%

    No Known Activations