© 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. 12998
    Prev
    Next
    INDEX
    Explanations

    final product

    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
    üstü
    -0.10
    orch
    -0.10
    inator
    -0.10
    PathComponent
    -0.10
    abor
    -0.10
    appa
    -0.10
    abouts
    -0.09
    734
    -0.09
    ForObject
    -0.09
     nackte
    -0.09
    POSITIVE LOGITS
    ively
    0.21
    ivity
    0.16
     phẩm
    0.16
    ivities
    0.16
    swith
    0.14
    (s
    0.14
    /by
    0.13
    ron
    0.13
    ive
    0.13
    ç»ıçIJĨ
    0.12
    Activations Density 0.014%

    No Known Activations