© 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. 29373
    Prev
    Next
    INDEX
    Explanations

    defining terms or classification

    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
     nicknamed
    -0.11
     Pron
    -0.10
     Phonetic
    -0.10
     renamed
    -0.08
     Heller
    -0.08
     slander
    -0.08
     constitution
    -0.08
     slogans
    -0.08
    oro
    -0.08
    atra
    -0.08
    POSITIVE LOGITS
     term
    1.00
    term
    0.75
     Term
    0.67
    Term
    0.64
     terme
    0.57
    -term
    0.57
     terms
    0.57
    _term
    0.55
     TERM
    0.54
    (term
    0.54
    Activations Density 0.379%

    No Known Activations