© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43845
    Prev
    Next
    INDEX
    Explanations

    that is

    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
    ancell
    -0.12
    abil
    -0.09
     dign
    -0.09
    abel
    -0.09
     bog
    -0.09
    ाहà¤ķ
    -0.09
     ظرÙģ
    -0.08
    abilia
    -0.08
    odd
    -0.08
     equal
    -0.08
    POSITIVE LOGITS
     poss
    0.12
    poss
    0.11
     Poss
    0.10
     exist
    0.10
    997
    0.10
     Hobby
    0.10
     fluores
    0.10
     can
    0.09
     Ñģамов
    0.09
     contain
    0.09
    Activations Density 0.057%

    No Known Activations