© 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. 34691
    Prev
    Next
    INDEX
    Explanations

    definitions of "one who is"

    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
    eli
    -0.09
    rored
    -0.09
     Mich
    -0.08
     Westbrook
    -0.08
    LEX
    -0.08
    -and
    -0.08
    "":
    -0.08
     sep
    -0.08
     Wildlife
    -0.08
    rogate
    -0.08
    POSITIVE LOGITS
     ones
    0.11
    ÑĢова
    0.09
     Jacques
    0.09
    äºĮäºĮäºĮäºĮ
    0.09
     place
    0.09
     piv
    0.09
     clearing
    0.09
     Mouse
    0.09
     literally
    0.08
    Brightness
    0.08
    Activations Density 0.050%

    No Known Activations