© 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. 21607
    Prev
    Next
    INDEX
    Explanations

    there followed by punctuation

    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
     here
    -0.20
     aquÃŃ
    -0.14
     здеÑģÑĮ
    -0.14
     اÛĮÙĨجا
    -0.13
    è¿ĻéĩĮ
    -0.13
     aqui
    -0.12
     ÑĤÑĥÑĤ
    -0.12
    ãģĤãĤĭ
    -0.12
     ìĹ¬ê¸°
    -0.11
     ÙĩÙĨا
    -0.11
    POSITIVE LOGITS
    abouts
    0.23
    on
    0.17
    оÑĪ
    0.17
    fore
    0.16
    after
    0.16
    unto
    0.16
    for
    0.14
    ina
    0.14
    from
    0.14
    FORE
    0.14
    Activations Density 0.032%

    No Known Activations