© 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. 24823
    Prev
    Next
    INDEX
    Explanations

    involves a process or steps

    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
    atti
    -0.11
    wdx
    -0.11
    usher
    -0.09
    acente
    -0.08
    ESH
    -0.08
    .wx
    -0.08
    chyb
    -0.08
    åĮĸ
    -0.08
    asher
    -0.08
    .sul
    -0.08
    POSITIVE LOGITS
     Ñģобой
    0.13
     first
    0.10
     ÑģобоÑİ
    0.10
     step
    0.10
     starting
    0.09
     Step
    0.09
    vig
    0.09
     reaction
    0.09
    (ed
    0.09
    aska
    0.09
    Activations Density 0.007%

    No Known Activations