© 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. 88265
    Prev
    Next
    INDEX
    Explanations

    references to historical events involving maritime elements or lighthouses

    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
     lakes
    -0.09
     lake
    -0.09
     Lake
    -0.08
    lake
    -0.08
     Mountain
    -0.07
    Lake
    -0.07
     Lakes
    -0.07
     pond
    -0.07
    ountain
    -0.07
     terrain
    -0.07
    POSITIVE LOGITS
     Cape
    0.11
     surf
    0.11
     cape
    0.10
     beach
    0.09
     Point
    0.09
    CAPE
    0.09
    surf
    0.09
     Coastal
    0.09
     bay
    0.08
     coastal
    0.08
    Activations Density 0.124%

    No Known Activations