© 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. 63404
    Prev
    Next
    INDEX
    Explanations

    remove unwanted characters or elements

    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
     Nile
    -0.10
    aro
    -0.09
     Andr
    -0.09
     Nie
    -0.09
    WithEmailAndPassword
    -0.08
    -icons
    -0.08
    achers
    -0.08
     Nielsen
    -0.08
    _retry
    -0.08
     Arbitrary
    -0.08
    POSITIVE LOGITS
     extr
    0.22
     excess
    0.19
    extr
    0.17
     unnecessary
    0.17
     Extr
    0.16
    æİī
    0.15
     лиÑĪ
    0.15
     khá»ıi
    0.14
     extra
    0.13
    åĨ
    0.13
    Activations Density 0.067%

    No Known Activations