© 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. 36564
    Prev
    Next
    INDEX
    Explanations

    handling situations

    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
    esson
    -0.09
    iden
    -0.09
    anian
    -0.09
     Ago
    -0.09
    utters
    -0.09
    ķĮ
    -0.08
    ething
    -0.08
    agens
    -0.08
     Cham
    -0.08
    enschaft
    -0.08
    POSITIVE LOGITS
     situation
    0.72
     Situation
    0.58
     situations
    0.52
     situación
    0.47
    æĥħåĨµ
    0.44
     ÑģиÑĤÑĥаÑĨии
    0.41
     situaci
    0.37
     situ
    0.36
    sit
    0.36
     situace
    0.36
    Activations Density 0.140%

    No Known Activations