© 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. 14695
    Prev
    Next
    INDEX
    Explanations

    напиÑģаÑĤÑĮ ÑģообÑīение

    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
    âĦĸâĦĸ
    -0.10
    ocre
    -0.09
    ÐIJÑĢÑħÑĸв
    -0.09
    екÑģи
    -0.09
    paralleled
    -0.09
    -urlencoded
    -0.09
    icrous
    -0.08
    .Messaging
    -0.08
    PTY
    -0.08
    èm
    -0.08
    POSITIVE LOGITS
     [_
    0.10
    ÄŁi
    0.10
    %@",
    0.09
    ģını
    0.09
    inine
    0.09
    ft
    0.08
    iling
    0.08
    _DT
    0.08
    Å¡em
    0.08
    irt
    0.08
    Activations Density 0.650%

    No Known Activations