© 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. 24072
    Prev
    Next
    INDEX
    Explanations

    boy in the street

    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
    æĪ¿
    -0.11
     room
    -0.10
     home
    -0.10
     backstage
    -0.10
    æĪ¿éĹ´
    -0.10
     wander
    -0.09
     phòng
    -0.09
    .ribbon
    -0.09
     guest
    -0.09
    ãĢĥ
    -0.09
    POSITIVE LOGITS
     street
    0.41
     streets
    0.38
    è¡Ĺ
    0.37
    street
    0.31
     Street
    0.28
     STREET
    0.28
    .street
    0.27
    Street
    0.26
     public
    0.25
     walking
    0.25
    Activations Density 0.243%

    No Known Activations