© 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. 24388
    Prev
    Next
    INDEX
    Explanations

    interesses, estratégias, ferramentas, avanços

    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
    croft
    -0.10
     various
    -0.10
     siguiente
    -0.09
     ï½Į
    -0.09
    oppel
    -0.09
     melhores
    -0.09
    astreet
    -0.08
    _Tab
    -0.08
     zbo
    -0.08
    evi
    -0.08
    POSITIVE LOGITS
    /or
    0.18
    /o
    0.16
    /of
    0.13
    jet
    0.11
    col
    0.11
    اسÙĩ
    0.11
    lor
    0.10
    νοÏį
    0.10
    uf
    0.10
    urch
    0.10
    Activations Density 0.079%

    No Known Activations