© 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. 28061
    Prev
    Next
    INDEX
    Explanations

    specific programming or coding terms and structures related to function definitions and error handling

    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
    cstring
    -0.06
     bead
    -0.06
    addock
    -0.06
    ekk
    -0.06
    nof
    -0.06
     anda
    -0.06
    customerId
    -0.05
    chool
    -0.05
    prung
    -0.05
     Propel
    -0.05
    POSITIVE LOGITS
     ãĢij
    0.07
     ấy
    0.07
    .Stretch
    0.07
    .dtd
    0.07
    .Paint
    0.06
     ;č↵
    0.06
    erule
    0.06
    èĬ³
    0.06
    obs
    0.06
    MLS
    0.06
    Activations Density 0.022%

    No Known Activations