© 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. 36156
    Prev
    Next
    INDEX
    Explanations

    announcement begins

    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
    #region
    -0.12
    ''"
    -0.09
     envelope
    -0.09
    raki
    -0.09
    anoi
    -0.09
    elp
    -0.09
     Sax
    -0.09
    anzi
    -0.09
     /*č\n
    -0.09
     Hog
    -0.09
    POSITIVE LOGITS
    #endregion
    0.17
     endregion
    0.15
    endregion
    0.14
    ï¼½
    0.13
    {/
    0.13
    [/
    0.12
    #End
    0.12
     </>\n
    0.11
    @endif
    0.11
    ï½£
    0.10
    Activations Density 0.078%

    No Known Activations