© 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. 44723
    Prev
    Next
    INDEX
    Explanations

    training dataset examples

    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
     Dün
    -0.12
    ableObject
    -0.10
    upy
    -0.10
    caf
    -0.10
    ç²
    -0.09
    EMPLARY
    -0.09
     shri
    -0.09
    ENU
    -0.09
    opp
    -0.09
    ESIS
    -0.09
    POSITIVE LOGITS
     representative
    0.14
     Representative
    0.11
     withheld
    0.11
     withholding
    0.11
     training
    0.10
     representatives
    0.10
    /task
    0.10
     closely
    0.09
     withhold
    0.09
     gold
    0.09
    Activations Density 0.073%

    No Known Activations