© 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. 15-LLAMASCOPE-RES-131K
    11. 90856
    Prev
    Next
    INDEX
    Explanations

    conditional and looping constructs in programming

    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
    /stretch
    -0.07
    Specifier
    -0.07
    strup
    -0.07
    олÑĥÑĩ
    -0.07
    ysl
    -0.06
    ẹp
    -0.06
     Ãĸl
    -0.06
    codegen
    -0.06
     æĿ
    -0.06
    ä¸įäºĨ
    -0.06
    POSITIVE LOGITS
    aver
    0.07
    acket
    0.06
    ruit
    0.06
    {}
    0.06
    aviest
    0.06
    Principal
    0.06
     ÑģÑĥÑĤ
    0.06
    å¼ı
    0.05
    igli
    0.05
    naments
    0.05
    Activations Density 0.005%

    No Known Activations