© 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. 34050
    Prev
    Next
    INDEX
    Explanations

    by phrases

    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
    WithName
    -0.09
    WithEmail
    -0.09
    /Dk
    -0.08
    trx
    -0.08
    ugin
    -0.08
     findOne
    -0.08
    entes
    -0.08
    sWith
    -0.08
    AndView
    -0.07
    اخت
    -0.07
    POSITIVE LOGITS
     by
    0.63
     oleh
    0.45
    by
    0.42
    _by
    0.40
     تÙĪسط
    0.39
    çĶ±
    0.38
     By
    0.38
     bằng
    0.37
     bợi
    0.35
     çĶ±
    0.35
    Activations Density 0.091%

    No Known Activations