© 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. 4969
    Prev
    Next
    INDEX
    Explanations

    section or article references

    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
    hcp
    -0.10
     )\n\n\n\n\n\n\n\n
    -0.09
    uxtap
    -0.09
     Germ
    -0.09
    AEA
    -0.08
     Supreme
    -0.08
     Deutsch
    -0.08
    çķ
    -0.08
    itto
    -0.08
    ayne
    -0.08
    POSITIVE LOGITS
    azio
    0.10
    ************************************************************************
    0.10
    imest
    0.09
    istas
    0.09
    adia
    0.09
     wrongful
    0.09
    ĕ
    0.09
    152
    0.08
    (s
    0.08
    ismo
    0.08
    Activations Density 0.034%

    No Known Activations