© 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 EvalsExportsinterp-engineNEWAPI 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. 104475
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax or structures, particularly those concerning arguments in functions and methods

    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
    wald
    -0.09
    azu
    -0.08
    å®ļçļĦ
    -0.08
    rende
    -0.07
    ä¹ĭä¸Ģ
    -0.07
    irl
    -0.07
    ynes
    -0.07
    attle
    -0.07
     Leban
    -0.07
    obel
    -0.07
    POSITIVE LOGITS
    args
    0.09
     args
    0.08
    arg
    0.07
    AREST
    0.06
    ARG
    0.06
     rest
    0.06
    erna
    0.06
    ай
    0.06
    igham
    0.06
    RTC
    0.06
    Activations Density 0.001%

    No Known Activations