© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 62156
    Prev
    Next
    INDEX
    Explanations

    references to an art gallery or cultural institutions

    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
     eskort
    -0.08
    辺
    -0.07
     Ск
    -0.07
    cheid
    -0.07
    hir
    -0.07
    venir
    -0.07
    menin
    -0.07
     meiden
    -0.07
    _emit
    -0.07
     prav
    -0.07
    POSITIVE LOGITS
     Dutch
    0.15
    .nl
    0.14
     van
    0.14
     Netherlands
    0.13
     Van
    0.13
     Amsterdam
    0.11
     Gron
    0.10
    _nl
    0.10
     Nederland
    0.10
    Van
    0.10
    Activations Density 0.311%

    No Known Activations