© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 4376
    Prev
    Next
    INDEX
    Explanations

    coding-related syntax elements, particularly those associated with setting frame sizes and positions in a user interface

    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
    ãģ¨ãģĨ
    -0.08
    blink
    -0.07
    rysler
    -0.07
    ivor
    -0.07
    omik
    -0.07
    ÑĥÑĢн
    -0.07
    -turned
    -0.06
     mét
    -0.06
    .prepend
    -0.06
    (åľŁ
    -0.06
    POSITIVE LOGITS
     Lust
    0.06
     Yar
    0.06
     createContext
    0.06
     Willis
    0.06
    wart
    0.06
    vere
    0.06
    ect
    0.05
    (QtCore
    0.05
    issing
    0.05
     McD
    0.05
    Activations Density 0.004%

    No Known Activations