© 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. 29502
    Prev
    Next
    INDEX
    Explanations

    is

    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
    ahat
    -0.09
    icont
    -0.09
    kest
    -0.09
     ever
    -0.09
    ocz
    -0.09
    qml
    -0.08
    uls
    -0.08
    aset
    -0.08
    ÃĹ\n\n
    -0.08
     unrecognized
    -0.08
    POSITIVE LOGITS
     remains
    0.33
     unknown
    0.33
     remain
    0.28
     unclear
    0.27
    unknown
    0.26
     Unknown
    0.24
    remain
    0.23
     remained
    0.22
    Unknown
    0.22
     descon
    0.20
    Activations Density 0.105%

    No Known Activations