© 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. 30353
    Prev
    Next
    INDEX
    Explanations

    interestingfascinatingfind interesting

    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
    azer
    -0.09
    incl
    -0.09
     inclined
    -0.09
    ori
    -0.09
     incl
    -0.09
     huz
    -0.08
     mun
    -0.08
     Lil
    -0.08
    ongan
    -0.08
    ichick
    -0.08
    POSITIVE LOGITS
     interesting
    0.39
     interess
    0.34
    interesting
    0.33
     инÑĤеÑĢеÑģ
    0.33
     fasc
    0.33
     interes
    0.32
     intéress
    0.31
     Fasc
    0.30
    Interesting
    0.30
    -interest
    0.29
    Activations Density 0.269%

    No Known Activations