© 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. 58905
    Prev
    Next
    INDEX
    Explanations

    whisper, deeds haunting, speak of

    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
     shri
    -0.12
     shouted
    -0.10
     teasing
    -0.10
    teÅŁ
    -0.10
     scream
    -0.10
     Laugh
    -0.10
     screams
    -0.09
    bach
    -0.09
     stamp
    -0.09
     screamed
    -0.09
    POSITIVE LOGITS
     whisper
    0.40
     whispers
    0.36
     whispered
    0.35
     Whisper
    0.35
     mur
    0.33
    wh
    0.27
    isper
    0.25
    -wh
    0.25
     Mur
    0.24
    Wh
    0.23
    Activations Density 0.130%

    No Known Activations