© 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. 62694
    Prev
    Next
    INDEX
    Explanations

    refers to a type of

    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
     Abb
    -0.11
    ubi
    -0.11
     abbrev
    -0.11
    Abb
    -0.10
     habitual
    -0.10
     quot
    -0.10
     unnamed
    -0.09
     renamed
    -0.09
     abbreviation
    -0.09
     dubbed
    -0.09
    POSITIVE LOGITS
     name
    0.19
     refers
    0.17
     reference
    0.15
     referring
    0.14
     refer
    0.14
     اشارÙĩ
    0.13
    æĺ¯ä¸Ģ
    0.13
    æĺ¯ä¸Ģ个
    0.12
    åIJį称
    0.12
     tên
    0.11
    Activations Density 0.190%

    No Known Activations