© 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. 30153
    Prev
    Next
    INDEX
    Explanations

    speaker, speakers

    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
    æ¹
    -0.10
    å±
    -0.10
    chet
    -0.10
     sigh
    -0.09
    åij¼
    -0.08
     vert
    -0.08
    antro
    -0.08
     Sensor
    -0.08
     cues
    -0.08
    Sensor
    -0.08
    POSITIVE LOGITS
     speakers
    0.46
     speaker
    0.45
     Speakers
    0.37
     Speaker
    0.36
    speaker
    0.31
    Speaker
    0.30
    -spe
    0.26
    peaker
    0.24
    Spe
    0.22
    spe
    0.22
    Activations Density 0.059%

    No Known Activations