© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35574
    Prev
    Next
    INDEX
    Explanations

    in + place names

    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
     Michigan
    -0.12
    Michigan
    -0.12
     Yemen
    -0.11
     liver
    -0.11
     Liver
    -0.11
     Crosby
    -0.11
    burgh
    -0.10
    jax
    -0.10
     Pittsburgh
    -0.10
     اÙĦÙĬÙħÙĨ
    -0.10
    POSITIVE LOGITS
     Hen
    0.22
    Hen
    0.18
     Philadelphia
    0.15
     Iowa
    0.15
     Bihar
    0.15
    Philadelphia
    0.14
     hen
    0.14
     Philly
    0.12
    éĥij
    0.12
     Glouce
    0.12
    Activations Density 0.082%

    No Known Activations