© 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. 40749
    Prev
    Next
    INDEX
    Explanations

    not a, non-, both foreign, any major

    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
     dispar
    -0.10
    negative
    -0.09
    Negative
    -0.09
     wÅĤa
    -0.09
     Casual
    -0.09
    aac
    -0.09
     negative
    -0.09
     competit
    -0.09
     militar
    -0.09
    è´Ł
    -0.09
    POSITIVE LOGITS
     worse
    0.13
     necessarily
    0.12
     worst
    0.12
     mild
    0.11
     abstract
    0.10
     reversible
    0.10
     directed
    0.10
     physical
    0.10
     targeting
    0.10
     imperson
    0.09
    Activations Density 0.172%

    No Known Activations