© 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. 49613
    Prev
    Next
    INDEX
    Explanations

    shown/found/proven/known to

    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
    ses
    -0.10
    itler
    -0.09
     Hath
    -0.09
     bagi
    -0.09
    #af
    -0.09
    æľ«
    -0.09
    _tF
    -0.09
     PlzeÅĪ
    -0.09
    ervas
    -0.09
     Burr
    -0.09
    POSITIVE LOGITS
     promise
    0.14
     sÄĥ
    0.12
     να
    0.12
     to
    0.11
     Promise
    0.11
    åħ·æľī
    0.10
    promise
    0.09
    Promise
    0.09
    renc
    0.09
     guilty
    0.09
    Activations Density 0.014%

    No Known Activations