© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 36540
    Prev
    Next
    INDEX
    Explanations

    can determine or create

    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
    uhan
    -0.09
    dit
    -0.09
    332
    -0.09
    à¹ĩà¸ķาม
    -0.09
    .isNotBlank
    -0.08
     resulting
    -0.08
    .rd
    -0.08
     Fame
    -0.08
     ext
    -0.08
     Sax
    -0.08
    POSITIVE LOGITS
     можно
    0.15
     podemos
    0.15
     можна
    0.13
     you
    0.13
     można
    0.12
    atz
    0.12
     we
    0.12
     puedo
    0.12
    åı¯ä»¥
    0.11
    èĥ½å¤Ł
    0.11
    Activations Density 0.027%

    No Known Activations