© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38315
    Prev
    Next
    INDEX
    Explanations

    eliminating creatures and monsters

    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
    Negative Logits
     Elf
    -0.10
     reinc
    -0.10
     Dwarf
    -0.09
    orris
    -0.09
     elves
    -0.09
     Frog
    -0.08
    quine
    -0.08
    é¸
    -0.08
    elper
    -0.08
     ByteArray
    -0.08
    POSITIVE LOGITS
     monsters
    0.22
     monster
    0.19
     enemy
    0.16
     огÑĢа
    0.15
     enemies
    0.15
     entities
    0.14
     creature
    0.14
     creatures
    0.14
     crit
    0.14
    Creat
    0.14
    Activations Density 0.143%

    No Known Activations