© 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. 36103
    Prev
    Next
    INDEX
    Explanations

    different types of things

    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
     standpoint
    -0.10
     timeframe
    -0.10
    ulan
    -0.10
     viewpoint
    -0.10
    avel
    -0.09
    ese
    -0.09
     duż
    -0.09
    諸
    -0.09
    morgan
    -0.09
    438
    -0.08
    POSITIVE LOGITS
    iable
    0.20
     sets
    0.19
    iating
    0.18
     approaches
    0.16
     respective
    0.16
     histories
    0.16
     degrees
    0.15
     styles
    0.15
     amounts
    0.15
     ways
    0.15
    Activations Density 0.078%

    No Known Activations