© 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. 24094
    Prev
    Next
    INDEX
    Explanations

    identifying verbs and linguistic structures

    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
     Vocabulary
    -0.12
     gramm
    -0.11
     Phrase
    -0.11
     phrases
    -0.11
     Vic
    -0.10
     Bout
    -0.10
     phon
    -0.10
     spelling
    -0.10
     subtitle
    -0.10
     syntax
    -0.10
    POSITIVE LOGITS
     verb
    0.52
    verb
    0.45
     Verb
    0.45
    Verb
    0.41
     verbs
    0.41
     VER
    0.33
    verbs
    0.32
     Ver
    0.29
    VER
    0.29
    Ver
    0.29
    Activations Density 0.309%

    No Known Activations