© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 28053
    Prev
    Next
    INDEX
    Explanations

    lines of code or programming-related syntax

    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
    atrix
    -0.06
     Rebellion
    -0.06
    DDS
    -0.06
    Abb
    -0.06
    jo
    -0.06
     poor
    -0.06
    735
    -0.06
    icol
    -0.06
     Poor
    -0.06
     trim
    -0.06
    POSITIVE LOGITS
    leigh
    0.08
    _TB
    0.07
    Pooling
    0.07
     codes
    0.07
     Chart
    0.07
    _Char
    0.07
    ulta
    0.07
    rack
    0.07
    CHANT
    0.07
    Codes
    0.07
    Activations Density 0.056%

    No Known Activations