© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 13514
    Prev
    Next
    INDEX
    Explanations

    coin flip outcomes

    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
    enas
    -0.11
    wert
    -0.09
    ings
    -0.09
     Chess
    -0.08
     scoring
    -0.08
     Scot
    -0.08
     Trap
    -0.08
    οÏħλ
    -0.08
     Rec
    -0.08
     Walter
    -0.08
    POSITIVE LOGITS
     coin
    0.35
     toss
    0.28
    coin
    0.27
     Coin
    0.25
     flip
    0.24
     coins
    0.23
     tossed
    0.22
     tossing
    0.22
    Coin
    0.21
     draw
    0.21
    Activations Density 0.140%

    No Known Activations