© 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. 25315
    Prev
    Next
    INDEX
    Explanations

    ing, ation, elling, arding, essing

    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
    ively
    -0.10
    inely
    -0.10
    ingly
    -0.10
    fds
    -0.09
    lessly
    -0.09
    ropriate
    -0.08
    imately
    -0.08
    itates
    -0.08
    ifique
    -0.08
    ame
    -0.08
    POSITIVE LOGITS
    ing
    0.19
    ening
    0.16
    ization
    0.15
    ting
    0.15
    uing
    0.15
    ming
    0.15
    ning
    0.14
    bing
    0.14
    cing
    0.13
    izing
    0.13
    Activations Density 0.185%

    No Known Activations