© 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. 26376
    Prev
    Next
    INDEX
    Explanations

    which is / that introduces

    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
     noun
    -0.13
    noun
    -0.12
     conson
    -0.11
     vowels
    -0.10
     term
    -0.10
     nouns
    -0.10
     pronunciation
    -0.10
     pronounce
    -0.10
     verb
    -0.10
    uthor
    -0.09
    POSITIVE LOGITS
     functioning
    0.16
     functions
    0.12
    Cour
    0.11
     modal
    0.11
     formation
    0.10
     past
    0.10
    -function
    0.10
     Cour
    0.10
    esome
    0.10
    -formed
    0.10
    Activations Density 0.131%

    No Known Activations