© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 42703
    Prev
    Next
    INDEX
    Explanations

    conditions

    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
    531
    -0.09
    tb
    -0.08
    ergy
    -0.08
    utral
    -0.08
     Sting
    -0.08
    /navigation
    -0.08
    lington
    -0.08
    dden
    -0.08
     Sphere
    -0.08
    466
    -0.08
    POSITIVE LOGITS
     conditions
    0.77
     Conditions
    0.62
    conditions
    0.62
    Conditions
    0.55
     CONDITIONS
    0.48
     condiciones
    0.48
    æĿ¡ä»¶
    0.46
    _conditions
    0.45
     ÑĥÑģловиÑı
    0.45
    .conditions
    0.40
    Activations Density 0.079%

    No Known Activations