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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 11699
    Prev
    Next
    INDEX
    Explanations

    land and shore descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oceans
    -0.22
     ocean
    -0.19
     lake
    -0.19
     Seas
    -0.18
     Atlantic
    -0.17
     Lake
    -0.17
     seas
    -0.16
     pond
    -0.15
    Atlantic
    -0.15
    Lake
    -0.15
    POSITIVE LOGITS
     land
    0.28
     shore
    0.27
    岸
    0.23
     беÑĢег
    0.21
    éĻ¸
    0.20
     mainland
    0.20
    éĻĨ
    0.20
     rocks
    0.17
    shore
    0.16
    land
    0.15
    Activations Density 0.044%

    No Known Activations