© 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. 24885
    Prev
    Next
    INDEX
    Explanations

    I must be statements

    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
    IENT
    -0.09
    ONSE
    -0.09
    277
    -0.09
     bordel
    -0.09
     alb
    -0.09
     Gomez
    -0.08
     Surprise
    -0.08
    imento
    -0.08
     Widgets
    -0.08
    åѦä¼ļ
    -0.08
    POSITIVE LOGITS
     girl
    0.11
     resc
    0.10
     date
    0.10
    å·§
    0.10
     crush
    0.10
    datable
    0.09
     hi
    0.09
     Girl
    0.09
     compliments
    0.09
     unp
    0.09
    Activations Density 0.105%

    No Known Activations