© 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. 35644
    Prev
    Next
    INDEX
    Explanations

    specifying word count

    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
    .Fat
    -0.09
    ISCO
    -0.09
     dụ
    -0.09
     Hubb
    -0.09
     Canary
    -0.08
     Byl
    -0.08
    bubble
    -0.08
    ÎŃαÏĤ
    -0.08
    _mo
    -0.08
     DEALINGS
    -0.08
    POSITIVE LOGITS
     words
    0.12
     Word
    0.11
     WORD
    0.10
     word
    0.10
    odd
    0.10
     Odd
    0.10
     range
    0.10
    ãģ«ãģĭ
    0.09
    Odd
    0.09
    ckill
    0.09
    Activations Density 0.039%

    No Known Activations