© 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. 56602
    Prev
    Next
    INDEX
    Explanations

    generating keywords

    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
     Kare
    -0.10
     pronunciation
    -0.09
    ayer
    -0.09
    logue
    -0.09
    rani
    -0.09
    aleur
    -0.09
     Phonetic
    -0.09
    idl
    -0.09
     Kauf
    -0.09
     Alphabet
    -0.08
    POSITIVE LOGITS
     keywords
    0.42
     Keywords
    0.36
    Keywords
    0.35
    keywords
    0.35
     keyword
    0.31
    åħ³éĶ®
    0.29
    _keywords
    0.27
    _KEYWORD
    0.25
    .keywords
    0.25
    keyword
    0.25
    Activations Density 0.209%

    No Known Activations