© 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
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44713
    Prev
    Next
    INDEX
    Explanations

    like quotes or thoughts

    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
     “;â̦
    -0.10
     Bye
    -0.10
    PEAT
    -0.09
    alth
    -0.08
    Verdana
    -0.08
    -ie
    -0.08
    uhl
    -0.08
    >NN
    -0.08
    bye
    -0.08
    ":č\n
    -0.08
    POSITIVE LOGITS
     "
    0.20
    ãĢĮæĪij
    0.14
     '
    0.14
     “;
    0.13
    :
    0.13
    "This
    0.11
    ãĢĮ
    0.10
    ï½¢
    0.10
    "Oh
    0.10
    ãĢĮä½ł
    0.10
    Activations Density 0.160%

    No Known Activations