© 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. 28486
    Prev
    Next
    INDEX
    Explanations

    difference between

    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
    ly
    -0.11
    ings
    -0.10
    ties
    -0.09
    ture
    -0.09
    est
    -0.09
    eda
    -0.09
    ities
    -0.09
    shot
    -0.09
     gros
    -0.08
    rek
    -0.08
    POSITIVE LOGITS
    ials
    0.24
    iating
    0.22
    iable
    0.19
    iator
    0.19
    iates
    0.18
    ially
    0.18
    iators
    0.17
    icult
    0.15
    iculty
    0.15
    iability
    0.15
    Activations Density 0.028%

    No Known Activations