© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 8091
    Prev
    Next
    INDEX
    Explanations

    do not give explanations

    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
    Negative Logits
    ison
    -0.09
     somew
    -0.08
    å«
    -0.08
    Ñİ
    -0.08
    eger
    -0.08
    459
    -0.08
    )throws
    -0.08
     доволÑĮно
    -0.08
     hatch
    -0.08
    otten
    -0.08
    POSITIVE LOGITS
     anything
    0.30
     any
    0.27
    ä»»ä½ķ
    0.26
    anything
    0.24
     Anything
    0.21
     ANY
    0.19
    Anything
    0.19
     anymore
    0.18
    any
    0.17
     qualquer
    0.16
    Activations Density 0.124%

    No Known Activations