© 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. 58877
    Prev
    Next
    INDEX
    Explanations

    assistant must say

    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
    345
    -0.10
    EMPLARY
    -0.09
    .Undef
    -0.09
    lyph
    -0.09
    .Classes
    -0.09
    terminate
    -0.09
     CrossAxisAlignment
    -0.09
    inant
    -0.09
    IIIK
    -0.09
    âĦĸâĦĸ
    -0.08
    POSITIVE LOGITS
     say
    0.18
     saying
    0.16
     finish
    0.15
     says
    0.15
     finishes
    0.13
     finishing
    0.13
     Say
    0.13
     continuation
    0.13
     said
    0.13
     continu
    0.12
    Activations Density 0.034%

    No Known Activations