© 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. 13831
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by conjunctions or starting words

    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
     nay
    -0.15
     -*-č\n
    -0.13
     addCriterion
    -0.13
     Nay
    -0.11
    ¶Į
    -0.10
    Â
    -0.10
    /Dk
    -0.10
    Ｖ
    -0.10
    TRGL
    -0.10
    ystack
    -0.09
    POSITIVE LOGITS
    --
    0.12
     nor
    0.11
     And
    0.10
    And
    0.10
     Mark
    0.09
    127
    0.09
    of
    0.09
    984
    0.09
     &,
    0.09
     O
    0.08
    Activations Density 0.091%

    No Known Activations