© 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. 25462
    Prev
    Next
    INDEX
    Explanations

    It is important or worth noting

    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
    431
    -0.10
    ses
    -0.09
    ÏĥÏĦε
    -0.09
    eca
    -0.09
    avit
    -0.08
    holds
    -0.08
     Herc
    -0.08
    ieg
    -0.08
    offs
    -0.08
    aded
    -0.08
    POSITIVE LOGITS
     worth
    0.28
    worth
    0.22
     Worth
    0.21
     should
    0.17
    should
    0.16
     important
    0.14
     sollte
    0.13
     ÑģÑĤоиÑĤ
    0.13
    Should
    0.12
    .IsAny
    0.12
    Activations Density 0.024%

    No Known Activations