© 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. 21662
    Prev
    Next
    INDEX
    Explanations

    by [name] or [role]

    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
     rock
    -0.10
     Graz
    -0.10
     ag
    -0.10
     pub
    -0.09
     Anth
    -0.09
     loc
    -0.09
     mass
    -0.09
     Sands
    -0.09
     Gerr
    -0.09
     Aeros
    -0.09
    POSITIVE LOGITS
     Chill
    0.13
     vapor
    0.11
     Peach
    0.11
     Cosby
    0.11
     instrumental
    0.11
     electronic
    0.10
     Bedroom
    0.10
     bedroom
    0.10
     trap
    0.10
     chilled
    0.09
    Activations Density 0.063%

    No Known Activations