© 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. 55411
    Prev
    Next
    INDEX
    Explanations

    Spanish, Italian, and Portuguese conjunctions/verbs

    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
    acente
    -0.18
     presente
    -0.17
    regor
    -0.13
     disponible
    -0.13
    еннаÑı
    -0.13
     коÑĤоÑĢое
    -0.13
     itself
    -0.12
    аннÑĭй
    -0.12
    еннÑĭй
    -0.12
     herself
    -0.12
    POSITIVE LOGITS
     ones
    0.21
     denen
    0.21
     коÑĤоÑĢÑĭе
    0.21
    izados
    0.21
    ulares
    0.19
     ÑĤакими
    0.19
     themselves
    0.18
    acionales
    0.18
    ленÑĭ
    0.17
    ificados
    0.17
    Activations Density 0.283%

    No Known Activations