© 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. 84902
    Prev
    Next
    INDEX
    Explanations

    technical terms and syntax related to programming, particularly in code snippets

    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
     огÑĢа
    -0.07
    idas
    -0.07
    iks
    -0.07
    hek
    -0.07
     Erotik
    -0.07
    _putchar
    -0.07
    EntryPoint
    -0.07
    isoner
    -0.07
    iaux
    -0.07
     Sır
    -0.07
    POSITIVE LOGITS
     Becker
    0.05
    GM
    0.05
     GM
    0.05
    145
    0.05
     Levine
    0.05
    èĶ
    0.05
    ÄĻż
    0.05
     otherwise
    0.05
    irut
    0.05
    UL
    0.05
    Activations Density 0.014%

    No Known Activations