© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 61416
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts related to enums and database configuration

    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
    วล
    -0.08
    IGHL
    -0.07
    BOUND
    -0.07
     Paginator
    -0.07
    .UTC
    -0.07
    ÙĪار
    -0.07
    antasy
    -0.07
    asje
    -0.07
    ignon
    -0.07
     Tie
    -0.06
    POSITIVE LOGITS
     enum
    0.10
    æŀļ
    0.09
    _enum
    0.09
     Enum
    0.08
    (enum
    0.08
    enum
    0.08
    _ENUM
    0.08
     enums
    0.08
    Enum
    0.08
    enums
    0.08
    Activations Density 0.080%

    No Known Activations