© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 69269
    Prev
    Next
    INDEX
    Explanations

    references to seawater and its applications or characteristics

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     lakes
    -0.09
    lake
    -0.07
     lake
    -0.07
    ountain
    -0.07
     Lakes
    -0.06
     Lake
    -0.06
    Lake
    -0.06
     Highland
    -0.06
    River
    -0.06
     Frost
    -0.06
    POSITIVE LOGITS
     sea
    0.14
     surf
    0.13
     beach
    0.13
     Cape
    0.12
     Sea
    0.12
     Beach
    0.11
     beaches
    0.11
    surf
    0.11
    æµ·
    0.11
    Sea
    0.11
    Activations Density 0.034%

    No Known Activations