© 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. 17338
    Prev
    Next
    INDEX
    Explanations

    by the way, by default, by using

    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
    ebin
    -0.09
    ÙĪÛĮد
    -0.09
    sez
    -0.08
    logg
    -0.08
     intim
    -0.08
    cribing
    -0.08
    맨
    -0.08
    DCALL
    -0.08
     mip
    -0.08
    jong
    -0.08
    POSITIVE LOGITS
     default
    0.25
     definition
    0.22
    gone
    0.21
     far
    0.20
     contrast
    0.18
    default
    0.18
     chance
    0.18
     nature
    0.17
    ron
    0.16
     way
    0.16
    Activations Density 0.029%

    No Known Activations