© 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. 34535
    Prev
    Next
    INDEX
    Explanations

    Check superstition

    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
     fantasy
    -0.10
     Fay
    -0.10
     Fantasy
    -0.09
    etes
    -0.09
     miracle
    -0.09
    lia
    -0.09
     strat
    -0.09
    ortal
    -0.08
    vu
    -0.08
     VT
    -0.08
    POSITIVE LOGITS
     luck
    0.39
     Luck
    0.35
    Luck
    0.32
     lucky
    0.29
    luck
    0.27
     unlucky
    0.24
     Lucky
    0.24
     superst
    0.24
     Ñĥда
    0.19
    fortune
    0.19
    Activations Density 0.075%

    No Known Activations