© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 44106
    Prev
    Next
    INDEX
    Explanations

    reading and measurement values

    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
     comb
    -0.11
     Inspection
    -0.10
     Tun
    -0.09
    <decltype
    -0.09
     Examination
    -0.09
     adjustable
    -0.09
    Regressor
    -0.09
     Visible
    -0.09
    pace
    -0.08
     overt
    -0.08
    POSITIVE LOGITS
     readings
    0.48
     reading
    0.33
     measurements
    0.30
    reading
    0.28
    Reading
    0.26
     Reading
    0.25
     recordings
    0.25
    _reading
    0.24
     measurement
    0.24
    READING
    0.23
    Activations Density 0.101%

    No Known Activations