© 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. 17-LLAMASCOPE-RES-131K
    11. 78845
    Prev
    Next
    INDEX
    Explanations

    references to museums and their attributes related to art and history

    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
    arent
    -0.08
    enza
    -0.07
    [unit
    -0.07
    åįĵ
    -0.07
    CRET
    -0.07
    cq
    -0.07
    irut
    -0.07
    835
    -0.07
    _PCIE
    -0.07
    ç
    -0.07
    POSITIVE LOGITS
     medicine
    0.08
     Medicine
    0.06
     contemporary
    0.06
    edicine
    0.06
     str
    0.06
     Contemporary
    0.06
    oppins
    0.06
    medicine
    0.06
    anks
    0.06
     ISSN
    0.06
    Activations Density 0.008%

    No Known Activations