© 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. 42794
    Prev
    Next
    INDEX
    Explanations

    capital cities, cabinets, change, taking

    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
     ðŁĺī\n\n
    -0.09
     ðŁĻĤ\n\n
    -0.09
    _pb
    -0.08
    ((((
    -0.08
    Separated
    -0.08
    ùa
    -0.08
    .apiUrl
    -0.08
    ehir
    -0.07
    âĢ
    -0.07
     antioxid
    -0.07
    POSITIVE LOGITS
    endregion
    0.11
    sto
    0.10
    Intialized
    0.09
     sto
    0.09
    @endsection
    0.09
     @}
    0.08
    ï¿
    0.08
    @endif
    0.08
    #endregion
    0.07
     Riv
    0.07
    Activations Density 0.075%

    No Known Activations