© 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. 20230
    Prev
    Next
    INDEX
    Explanations

    amaba a su pueblo

    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
     nuest
    -0.12
    ê¸Ķ
    -0.10
     ourselves
    -0.10
     myself
    -0.09
     your
    -0.09
     minha
    -0.09
     nossa
    -0.09
     nostra
    -0.09
    ustos
    -0.09
     oggi
    -0.09
    POSITIVE LOGITS
     vag
    0.11
     Fol
    0.10
     fol
    0.09
     incred
    0.09
    帮åĬ©
    0.09
     vener
    0.09
     himself
    0.09
     his
    0.09
    atem
    0.08
     Nap
    0.08
    Activations Density 0.056%

    No Known Activations