© 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. 58270
    Prev
    Next
    INDEX
    Explanations

    takes another function or class

    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
    ael
    -0.08
    ymous
    -0.08
    isoft
    -0.08
    .additional
    -0.07
     تط
    -0.07
    ril
    -0.07
    lbrace
    -0.07
    andes
    -0.07
    rado
    -0.07
    inya
    -0.07
    POSITIVE LOGITS
     another
    0.92
    another
    0.73
     Another
    0.65
    åı¦
    0.62
    Another
    0.61
    åı¦ä¸Ģ
    0.56
     otro
    0.53
     otra
    0.51
     other
    0.48
     baÅŁka
    0.47
    Activations Density 0.426%

    No Known Activations