© 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. 63373
    Prev
    Next
    INDEX
    Explanations

    end of code blocks

    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
    738
    -0.09
     assignable
    -0.09
     Hubb
    -0.09
     Dew
    -0.08
     Carp
    -0.08
    iec
    -0.08
     Horde
    -0.08
    ier
    -0.08
     lut
    -0.08
     bod
    -0.08
    POSITIVE LOGITS
    }\n
    0.11
     Clair
    0.11
    ï½Ŀ
    0.11
     }\n
    0.10
     mist
    0.10
    £¼
    0.09
     à¸
    0.09
    eyin
    0.09
    }\
    0.09
     Slip
    0.09
    Activations Density 0.022%

    No Known Activations