© 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. 23488
    Prev
    Next
    INDEX
    Explanations

    pound of feathers, quando eu, Manchester City

    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
    CodeAt
    -0.09
     Tem
    -0.09
     Bombay
    -0.08
    otte
    -0.08
    endregion
    -0.08
     Chow
    -0.08
    riba
    -0.08
     erotique
    -0.08
    _HERSHEY
    -0.08
     furn
    -0.08
    POSITIVE LOGITS
     former
    0.10
    both
    0.10
     both
    0.09
    former
    0.09
    Appending
    0.08
    ï¿£
    0.08
     beiden
    0.08
    amas
    0.08
     Shannon
    0.08
    ë°
    0.08
    Activations Density 0.143%

    No Known Activations