© 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. 61427
    Prev
    Next
    INDEX
    Explanations

    savannah, savings, savage

    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
    orc
    -0.10
    eln
    -0.10
     surviving
    -0.09
    illos
    -0.09
    695
    -0.09
     Keller
    -0.09
    deb
    -0.09
    323
    -0.09
    well
    -0.09
    inta
    -0.09
    POSITIVE LOGITS
    InstanceState
    0.17
    OrUpdate
    0.14
    annah
    0.12
    vy
    0.12
    illance
    0.12
    aged
    0.11
    imuth
    0.11
    aging
    0.10
     grace
    0.10
     Sav
    0.10
    Activations Density 0.023%

    No Known Activations