© 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. 37009
    Prev
    Next
    INDEX
    Explanations

    answering questions and providing responses

    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
     superv
    -0.09
     tÆ°á»Łng
    -0.09
     adipiscing
    -0.08
    鹿
    -0.08
    uhe
    -0.08
     wield
    -0.08
     interviewing
    -0.08
     Ruby
    -0.08
     Request
    -0.08
     tink
    -0.08
    POSITIVE LOGITS
     answer
    0.37
    åĽŀçŃĶ
    0.29
     Answer
    0.28
     answered
    0.28
     respond
    0.28
     answers
    0.27
    answer
    0.27
    Answer
    0.26
    çŃĶ
    0.26
     répond
    0.25
    Activations Density 0.316%

    No Known Activations