© 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. 29872
    Prev
    Next
    INDEX
    Explanations

    creating software components

    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
    932
    -0.09
     chosen
    -0.08
     newly
    -0.08
     Zh
    -0.08
    amt
    -0.08
    327
    -0.08
    319
    -0.08
    da
    -0.08
     Wikipedia
    -0.08
     kterou
    -0.08
    POSITIVE LOGITS
     capable
    0.26
     able
    0.22
    èĥ½å¤Ł
    0.18
    èĥ½
    0.18
     èĥ½
    0.17
     that
    0.17
    that
    0.14
     who
    0.14
     коÑĤоÑĢаÑı
    0.14
     Able
    0.13
    Activations Density 0.228%

    No Known Activations