© 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. 33985
    Prev
    Next
    INDEX
    Explanations

    physical measurements and quantities

    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
    ¶Į
    -0.13
    âĦĸâĦĸ
    -0.10
    ÂĢÂĢ
    -0.10
    ******č\n
    -0.10
    .Formatter
    -0.09
    надлеж
    -0.09
    aeda
    -0.09
    ¦æĥħ
    -0.09
    ĤŃ
    -0.09
    mada
    -0.09
    POSITIVE LOGITS
     individual
    0.11
     full
    0.09
     Individual
    0.09
     entire
    0.09
    0.09
     directly
    0.08
    å®Įæķ´
    0.08
     physical
    0.08
     Full
    0.08
     direct
    0.08
    Activations Density 0.472%

    No Known Activations