© 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. 28461
    Prev
    Next
    INDEX
    Explanations

    what is considered normal

    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
    :::::::::::
    -0.09
    agit
    -0.09
    ouch
    -0.08
     Zwe
    -0.08
     comprom
    -0.08
     dazz
    -0.08
    awan
    -0.08
    ndon
    -0.08
    brit
    -0.08
    761
    -0.08
    POSITIVE LOGITS
     norm
    0.29
     normal
    0.28
    norm
    0.23
     Normal
    0.23
     Norm
    0.23
     NORMAL
    0.23
    normal
    0.22
     ноÑĢм
    0.22
    -normal
    0.21
     normalized
    0.21
    Activations Density 0.075%

    No Known Activations