© 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. 15432
    Prev
    Next
    INDEX
    Explanations

    existing techniques

    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
    ahan
    -0.09
    consistent
    -0.09
     Games
    -0.09
    _authenticated
    -0.08
    Anth
    -0.08
     exploiting
    -0.08
     particular
    -0.08
     plung
    -0.08
    843
    -0.08
    urst
    -0.08
    POSITIVE LOGITS
     existing
    0.41
     previous
    0.34
    existing
    0.30
     current
    0.29
     Existing
    0.29
    Existing
    0.29
     conventional
    0.27
     traditional
    0.27
    previous
    0.27
    -existing
    0.26
    Activations Density 0.121%

    No Known Activations