© 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. 40455
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and constants

    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
    esk
    -0.08
    жно
    -0.08
    ải
    -0.08
     STDCALL
    -0.08
    ̣
    -0.08
    ÑĪем
    -0.08
    elon
    -0.08
    ephy
    -0.08
    igure
    -0.08
    опол
    -0.08
    POSITIVE LOGITS
    <
    0.07
     themselves
    0.06
     <
    0.06
     Äijâu
    0.05
     Cham
    0.05
    0.05
    /
    0.05
     allot
    0.05
    oda
    0.05
    404
    0.05
    Activations Density 0.001%

    No Known Activations