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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44400
    Prev
    Next
    INDEX
    Explanations

    analyze signals

    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
     Pant
    -0.11
     wavelength
    -0.10
     pant
    -0.10
     dol
    -0.09
     simplex
    -0.09
    ÅĽci
    -0.09
     burning
    -0.09
     Vide
    -0.09
     wavelengths
    -0.08
     iceberg
    -0.08
    POSITIVE LOGITS
     signal
    0.36
     signals
    0.30
    signal
    0.29
     Signal
    0.25
     Signals
    0.23
    Signal
    0.23
    _signal
    0.23
    ä¿¡
    0.22
     Ñģиг
    0.21
    signals
    0.21
    Activations Density 0.058%

    No Known Activations