© 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. 31166
    Prev
    Next
    INDEX
    Explanations

    what's on your mind?

    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
     "?
    -0.11
    oui
    -0.10
     bother
    -0.10
    åIJĹ
    -0.10
    aders
    -0.09
    ä¹Ī
    -0.09
    iedade
    -0.09
    ?s
    -0.09
     ?????
    -0.09
    åĹİ
    -0.09
    POSITIVE LOGITS
     denn
    0.14
     exactly
    0.12
    ?\n
    0.12
     pray
    0.11
    -=
    0.10
     eigentlich
    0.10
    ?
    0.10
    ?\n\n
    0.09
     then
    0.09
    ?"\n
    0.09
    Activations Density 0.144%

    No Known Activations