© 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. 4708
    Prev
    Next
    INDEX
    Explanations

    speech, pronunciation, understanding

    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
     Lingu
    -0.18
     lingu
    -0.17
     languages
    -0.17
     linguistic
    -0.17
     Languages
    -0.17
     bilingual
    -0.16
    /language
    -0.15
    ilingual
    -0.12
    Languages
    -0.12
     learning
    -0.11
    POSITIVE LOGITS
     passive
    0.18
     conversation
    0.16
     speaking
    0.15
     listening
    0.15
     Passive
    0.13
     Listening
    0.13
    Conversation
    0.12
    conversation
    0.12
    Listening
    0.12
    spe
    0.12
    Activations Density 0.053%

    No Known Activations