© 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. 88385
    Prev
    Next
    INDEX
    Explanations

    special character patterns and symbols commonly used 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
    ève
    -0.07
    nap
    -0.07
    Violation
    -0.07
     Lug
    -0.06
    á»ĭ
    -0.06
    |(↵
    -0.06
    olo
    -0.06
     Revision
    -0.06
    lings
    -0.06
    -at
    -0.06
    POSITIVE LOGITS
    kwargs
    0.10
    ighton
    0.07
    unused
    0.07
    tics
    0.07
     ker
    0.07
    ahat
    0.06
     kwargs
    0.06
    anda
    0.06
    adoo
    0.06
    auge
    0.06
    Activations Density 0.001%

    No Known Activations