© 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. 25983
    Prev
    Next
    INDEX
    Explanations

    P.

    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
     ISBN
    -0.08
    ,\n\n\n\n
    -0.08
    prov
    -0.08
    1
    -0.08
    ãģĤãģĤ
    -0.08
    2
    -0.07
    prec
    -0.07
    3
    -0.07
    PropertyValue
    -0.07
    6
    -0.07
    POSITIVE LOGITS
     Pradesh
    0.10
    ÂłP
    0.10
     Ù¾ÛĮØ´ÛĮÙĨÙĩ
    0.10
    _P
    0.10
    ÂłÐ¿
    0.09
    ptest
    0.09
     Palestinians
    0.09
     PÅĺ
    0.09
    \tP
    0.09
     Peygamber
    0.09
    Activations Density 0.701%

    No Known Activations