© 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. 23334
    Prev
    Next
    INDEX
    Explanations

    NAME_1 placeholder

    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
    alin
    -0.10
     honeymoon
    -0.08
     acknowled
    -0.08
    ิà¸Ĺย
    -0.08
    rible
    -0.08
    loit
    -0.08
    uben
    -0.08
    ê´
    -0.08
    iras
    -0.08
     Negro
    -0.07
    POSITIVE LOGITS
    -style
    0.10
     yani
    0.09
     lá»Ńa
    0.09
     Buckingham
    0.08
    IPH
    0.08
    algo
    0.08
     style
    0.08
    lescope
    0.08
    =”;
    0.08
    enerator
    0.08
    Activations Density 0.257%

    No Known Activations