© 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. 35671
    Prev
    Next
    INDEX
    Explanations

    has been a subject

    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
     potentially
    -0.10
    SSIP
    -0.10
    iris
    -0.09
    omers
    -0.09
     Hamm
    -0.09
     Mund
    -0.09
    ÐIJÑĢÑħÑĸв
    -0.09
     currently
    -0.09
    uffman
    -0.09
     tod
    -0.09
    POSITIVE LOGITS
     since
    0.24
     recent
    0.18
     recently
    0.18
    since
    0.17
     lately
    0.17
    recent
    0.16
     thus
    0.14
    Recent
    0.14
    æľĢè¿ij
    0.14
    Recently
    0.14
    Activations Density 0.131%

    No Known Activations