© 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. 55784
    Prev
    Next
    INDEX
    Explanations

    like Google's Speech

    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
     Artifact
    -0.09
     Huffman
    -0.09
     Ih
    -0.09
     untranslated
    -0.08
     rele
    -0.08
     termin
    -0.08
    Automation
    -0.08
     Wyatt
    -0.08
     Pascal
    -0.08
     Raq
    -0.08
    POSITIVE LOGITS
     speech
    0.39
     voice
    0.38
     Voice
    0.35
     Speech
    0.34
    Speech
    0.32
    Voice
    0.30
    voice
    0.30
    speech
    0.29
    peech
    0.23
     голоÑģ
    0.23
    Activations Density 0.201%

    No Known Activations