© 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. 4715
    Prev
    Next
    INDEX
    Explanations

    referring resolve attend

    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
    upal
    -0.09
    ongyang
    -0.09
    786
    -0.08
     shall
    -0.08
     Nath
    -0.08
    ansi
    -0.08
    ucher
    -0.08
    âĢħ
    -0.08
    enment
    -0.08
    imeline
    -0.08
    POSITIVE LOGITS
    ahr
    0.08
     Revolution
    0.08
    assen
    0.08
    âĦ
    0.08
    ãĥ«ãĤ¯
    0.08
     substant
    0.08
     proverb
    0.07
    628
    0.07
     assistance
    0.07
    ROUP
    0.07
    Activations Density 0.076%

    No Known Activations