© 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. 56301
    Prev
    Next
    INDEX
    Explanations

    rather than its

    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
     formal
    -0.10
     perfect
    -0.10
    ugi
    -0.10
    ngr
    -0.09
    çļĦäºĭ
    -0.09
     Formal
    -0.09
     very
    -0.08
    absolute
    -0.08
    _hpp
    -0.08
     èİ
    -0.08
    POSITIVE LOGITS
     actually
    0.49
     actual
    0.43
    actually
    0.38
     Actually
    0.38
    å®ŀéĻħ
    0.35
    actual
    0.33
    Actually
    0.33
     Actual
    0.29
     ìĭ¤ìłľ
    0.29
    羣æŃ£
    0.28
    Activations Density 0.159%

    No Known Activations