© 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. 3823
    Prev
    Next
    INDEX
    Explanations

    the + word

    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
    aque
    -0.10
     renamed
    -0.10
    ingu
    -0.10
     alphabetical
    -0.10
     rename
    -0.10
    ÑĪка
    -0.09
    _ctxt
    -0.09
     //////////////////////////////////////////////////////////////////////
    -0.08
     renaming
    -0.08
    ache
    -0.08
    POSITIVE LOGITS
     word
    0.42
     words
    0.41
     phrase
    0.39
     term
    0.34
    word
    0.29
    words
    0.28
    phrase
    0.26
     palabra
    0.24
    -word
    0.23
     Ñģлово
    0.22
    Activations Density 0.173%

    No Known Activations