© 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. 18513
    Prev
    Next
    INDEX
    Explanations

    may need or require

    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
     można
    -0.09
     åĭ
    -0.09
    legs
    -0.09
     Mud
    -0.08
    inem
    -0.08
    awa
    -0.08
    __,__
    -0.08
     Flour
    -0.08
    &P
    -0.08
     DIC
    -0.08
    POSITIVE LOGITS
     need
    0.22
     require
    0.18
    éľĢè¦ģ
    0.18
     cần
    0.17
     needed
    0.16
    need
    0.16
    éľĢ
    0.15
     required
    0.15
     necessary
    0.15
     requires
    0.14
    Activations Density 0.047%

    No Known Activations