© 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. 107170
    Prev
    Next
    INDEX
    Explanations

    references to Git and various programming constructs or data types in code 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
    HIR
    -0.06
    каÑĢ
    -0.06
     Leer
    -0.06
    ovu
    -0.06
    izen
    -0.06
     æħ
    -0.06
     Od
    -0.06
    estre
    -0.06
    Ñħи
    -0.06
    олеÑĤ
    -0.06
    POSITIVE LOGITS
    _FILENO
    0.08
    RowAt
    0.07
    istrovstvÃŃ
    0.07
    ernetes
    0.07
    -aos
    0.07
    upil
    0.07
    sic
    0.07
    abo
    0.07
    ethoven
    0.06
    BeenCalled
    0.06
    Activations Density 0.050%

    No Known Activations