© 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. 58678
    Prev
    Next
    INDEX
    Explanations

    geographical locations

    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
    edly
    -0.09
    ÑģÑĤвÑĥ
    -0.09
    League
    -0.08
    -REAL
    -0.08
    -ÑĦ
    -0.08
     League
    -0.08
     harmony
    -0.08
     doma
    -0.08
    ses
    -0.08
    (s
    -0.08
    POSITIVE LOGITS
    shire
    0.18
    -area
    0.18
    ian
    0.17
    ans
    0.14
    -based
    0.14
    ensis
    0.14
    -born
    0.13
    ians
    0.13
    istan
    0.13
    ese
    0.12
    Activations Density 0.133%

    No Known Activations