© 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. 898
    Prev
    Next
    INDEX
    Explanations

    assinale a alternativa

    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
    -0.17
     follando
    -0.15
     ragaz
    -0.11
     ah
    -0.10
     rut
    -0.09
    añ
    -0.09
     person
    -0.09
     pract
    -0.09
     parallel
    -0.09
    <?\n
    -0.09
    POSITIVE LOGITS
     correct
    0.11
     tô
    0.10
    antro
    0.10
     nouve
    0.10
     Äijúng
    0.10
    æŃ£ç¡®
    0.10
     Wass
    0.10
     true
    0.10
    ãy
    0.09
    agher
    0.09
    Activations Density 0.198%

    No Known Activations