© 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. 58965
    Prev
    Next
    INDEX
    Explanations

    zones of certainty

    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
    Wrapped
    -0.09
     locality
    -0.09
    gere
    -0.08
     mole
    -0.08
     bout
    -0.08
    ãģĭãģij
    -0.08
    esson
    -0.08
    æŀĿ
    -0.08
     Ruth
    -0.08
     elapsed
    -0.08
    POSITIVE LOGITS
     zone
    0.47
     zones
    0.43
     Zone
    0.42
    zone
    0.37
    Zone
    0.35
     zona
    0.32
     Zones
    0.31
    -zone
    0.31
    ZONE
    0.30
    .zone
    0.28
    Activations Density 0.100%

    No Known Activations