© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 41257
    Prev
    Next
    INDEX
    Explanations

    wildlife including many species

    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
     rabbit
    -0.13
     frog
    -0.12
     dolphin
    -0.12
     kitten
    -0.12
     zo
    -0.12
     Frog
    -0.12
     underst
    -0.11
     Zo
    -0.11
     lizard
    -0.11
     Shark
    -0.11
    POSITIVE LOGITS
     rare
    0.19
    Rare
    0.13
     wild
    0.12
     seals
    0.12
     Rare
    0.12
     ib
    0.11
     bears
    0.11
     elusive
    0.11
    uars
    0.11
     rar
    0.11
    Activations Density 0.065%

    No Known Activations