© 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. 58003
    Prev
    Next
    INDEX
    Explanations

    pronoun or article after period

    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
     disgr
    -0.10
     However
    -0.10
    However
    -0.10
    дн
    -0.10
    plus
    -0.09
    ï¼Įä½Ĩæĺ¯
    -0.09
     Meanwhile
    -0.09
     HOWEVER
    -0.09
    inx
    -0.09
     particularly
    -0.09
    POSITIVE LOGITS
     totiž
    0.18
    Nam
    0.15
     Nam
    0.15
     Instead
    0.13
     instead
    0.13
    Instead
    0.13
     denn
    0.12
     turns
    0.11
     ведÑĮ
    0.11
     nam
    0.11
    Activations Density 0.089%

    No Known Activations