© 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 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. 128788
    Prev
    Next
    INDEX
    Explanations

    the structure and syntax of code, specifically focusing on conditional statements and variable assignments

    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
    s
    -0.10
    $MESS
    -0.07
    à¸ģาร
    -0.07
    Ø©
    -0.07
     Auth
    -0.07
    Ùĩ
    -0.07
    udeau
    -0.07
    ä¸Ģç§į
    -0.06
    ر
    -0.06
    asl
    -0.06
    POSITIVE LOGITS
    0.09
    soever
    0.08
     ActionTypes
    0.07
    RYPT
    0.07
    segue
    0.07
    ¯
    0.07
    entar
    0.06
    compat
    0.06
    arity
    0.06
    меÑĤÑĮ
    0.06
    Activations Density 0.099%

    No Known Activations