© 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. 51208
    Prev
    Next
    INDEX
    Explanations

    import speech as

    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
     Orchard
    -0.10
    æݧ
    -0.09
    uela
    -0.09
     Tone
    -0.09
     cil
    -0.09
    ernaut
    -0.09
     Spit
    -0.08
    олаг
    -0.08
     Lord
    -0.08
     SetLastError
    -0.08
    POSITIVE LOGITS
    /backend
    0.10
     klu
    0.10
     speech
    0.10
     speak
    0.09
    /Dk
    0.09
     )\n\n\n\n\n\n\n\n
    0.09
    plnÄĽ
    0.09
    AndWait
    0.09
     Speak
    0.09
     ï¿£
    0.09
    Activations Density 0.092%

    No Known Activations