© 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. 31205
    Prev
    Next
    INDEX
    Explanations

    minimum or at least

    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
    (MAX
    -0.12
     maximal
    -0.12
     xmax
    -0.11
    .maxLength
    -0.11
    .setMax
    -0.11
    MaxLength
    -0.11
    maxlength
    -0.11
    xmax
    -0.10
     maxX
    -0.10
    maxLength
    -0.10
    POSITIVE LOGITS
     minimum
    0.70
     Minimum
    0.56
    minimum
    0.55
    Minimum
    0.52
    èĩ³å°ij
    0.49
     mÃŃnimo
    0.46
    _minimum
    0.40
     миним
    0.38
     ØŃداÙĤÙĦ
    0.36
    .minimum
    0.35
    Activations Density 0.173%

    No Known Activations