© 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. 59241
    Prev
    Next
    INDEX
    Explanations

    be followed by descriptive verbs

    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
    imir
    -0.10
    obre
    -0.10
     meant
    -0.09
    ãĥĻãĥ«
    -0.09
     att
    -0.09
    ocode
    -0.09
    enton
    -0.09
     ï¾Ħ
    -0.09
     outnumber
    -0.09
     Reported
    -0.08
    POSITIVE LOGITS
     compared
    0.14
     described
    0.14
     seen
    0.13
     explained
    0.13
     broken
    0.12
     best
    0.11
     decom
    0.11
     defined
    0.11
     traced
    0.11
    broken
    0.11
    Activations Density 0.100%

    No Known Activations