© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 45415
    Prev
    Next
    INDEX
    Explanations

    indicates the reason for

    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
    nt
    -0.10
    336
    -0.10
    mer
    -0.10
    rien
    -0.10
    nect
    -0.09
    pher
    -0.09
    logo
    -0.09
     Tess
    -0.09
    uplic
    -0.09
    isse
    -0.09
    POSITIVE LOGITS
    à¸Ńà¸ĩà¸Īาà¸ģ
    0.27
    ñas
    0.14
    led
    0.13
     diligence
    0.13
    ños
    0.13
    æĸ¼
    0.12
    ño
    0.12
    ña
    0.11
     lack
    0.11
    -за
    0.11
    Activations Density 0.030%

    No Known Activations