© 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. 17904
    Prev
    Next
    INDEX
    Explanations

    current context

    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
     current
    -0.14
    CurrentValue
    -0.13
    å½ĵåīį
    -0.12
    CurrentUser
    -0.12
    utow
    -0.10
    _current
    -0.10
    çı¾
    -0.10
     íĺĦìŀ¬
    -0.10
     currentPlayer
    -0.09
    pedia
    -0.09
    POSITIVE LOGITS
    ãģ¨ãģĵãĤį
    0.18
    /form
    0.16
    -day
    0.15
    /original
    0.15
    iment
    0.14
    /new
    0.14
    /latest
    0.14
    ely
    0.13
    ;y
    0.12
     working
    0.12
    Activations Density 0.021%

    No Known Activations