© 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. 47141
    Prev
    Next
    INDEX
    Explanations

    write in style or only present facts

    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
    chang
    -0.09
     my
    -0.08
    ucch
    -0.08
    /messages
    -0.08
    wich
    -0.08
    036
    -0.08
     branding
    -0.08
    (Encoding
    -0.08
    ember
    -0.08
    }elseif
    -0.08
    POSITIVE LOGITS
     answer
    0.10
     loft
    0.09
     Hlav
    0.08
    errs
    0.08
    (answer
    0.08
    alc
    0.08
     münchen
    0.08
     topic
    0.08
     filib
    0.08
    /proto
    0.08
    Activations Density 0.233%

    No Known Activations