© 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. 31864
    Prev
    Next
    INDEX
    Explanations

    determines, followed, placed, from

    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
     autogenerated
    -0.10
     -*-č\n
    -0.10
    icter
    -0.10
    _SEP
    -0.08
    ìī¬
    -0.08
    á»ĵi
    -0.08
    pher
    -0.08
    _exceptions
    -0.08
    ILTER
    -0.08
    uby
    -0.08
    POSITIVE LOGITS
     else
    0.11
     again
    0.11
     otherwise
    0.10
    again
    0.10
     alternative
    0.09
     message
    0.09
     Plan
    0.09
     vice
    0.09
     yine
    0.09
     finally
    0.09
    Activations Density 0.008%

    No Known Activations