© 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. 13768
    Prev
    Next
    INDEX
    Explanations

    safe for use

    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
     slightest
    -0.10
     Eins
    -0.09
     tint
    -0.09
     عد
    -0.08
     Transfer
    -0.08
     sometimes
    -0.08
    ::::::::::::::
    -0.08
    oader
    -0.08
     Reich
    -0.08
     Cra
    -0.08
    POSITIVE LOGITS
     unless
    0.20
     normal
    0.18
     short
    0.17
    unless
    0.16
     moderate
    0.15
     most
    0.15
     brief
    0.14
     properly
    0.14
     Unless
    0.14
    æŃ£å¸¸
    0.14
    Activations Density 0.074%

    No Known Activations