© 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. 30043
    Prev
    Next
    INDEX
    Explanations

    Krishidoot Shikshan Bharati

    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
    ungle
    -0.11
    rah
    -0.11
    hawk
    -0.10
     Sai
    -0.10
    à¹īà¹ī
    -0.10
    adia
    -0.09
     naw
    -0.09
    croft
    -0.09
     Anders
    -0.09
     Clamp
    -0.09
    POSITIVE LOGITS
    esh
    0.13
    aved
    0.12
    sth
    0.12
    oday
    0.12
    ika
    0.11
     Sam
    0.11
     Sw
    0.11
    asy
    0.11
     Pr
    0.11
     Parish
    0.10
    Activations Density 0.063%

    No Known Activations