© 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. 27187
    Prev
    Next
    INDEX
    Explanations

    will possibly ever be

    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
     maybe
    -0.11
    739
    -0.10
     certain
    -0.10
     nothing
    -0.10
     neither
    -0.10
    aru
    -0.10
    atee
    -0.09
    è¿ĺæĺ¯
    -0.09
     Certain
    -0.09
     (++
    -0.08
    POSITIVE LOGITS
     ever
    0.74
    ever
    0.51
     EVER
    0.51
    -ever
    0.47
    Ever
    0.39
     Ever
    0.39
     jamais
    0.36
     à¤ķà¤Ń
    0.33
     any
    0.25
    ä»»ä½ķ
    0.22
    Activations Density 0.088%

    No Known Activations