© 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. 71331
    Prev
    Next
    INDEX
    Explanations

    instructions related to programming or algorithm design

    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
    èĶµ
    -0.07
    chten
    -0.07
    .ribbon
    -0.07
    bum
    -0.07
    åıİ
    -0.07
    æĴ
    -0.06
     blasting
    -0.06
    539
    -0.06
    cpy
    -0.06
    ÑĢаж
    -0.06
    POSITIVE LOGITS
    AREST
    0.06
    axon
    0.06
    oodle
    0.06
    æ³³
    0.06
     arte
    0.06
     Fot
    0.06
    IDDEN
    0.06
     biên
    0.06
    oscope
    0.05
    oose
    0.05
    Activations Density 0.004%

    No Known Activations