© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 58734
    Prev
    Next
    INDEX
    Explanations

    AI language model descriptions

    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
    /he
    -0.10
     bro
    -0.09
     Malk
    -0.09
    ิà¸ļ
    -0.08
     ãĢIJ
    -0.08
     Libert
    -0.08
    agas
    -0.08
    appy
    -0.08
     Horton
    -0.08
    /we
    -0.08
    POSITIVE LOGITS
     myself
    0.12
     AI
    0.10
    AI
    0.10
     tôi
    0.10
     ÙģØ¥ÙĨ
    0.09
    eteria
    0.09
     завиÑģим
    0.09
    EXTERN
    0.09
    _unset
    0.09
    ï¼ĮæĪij
    0.09
    Activations Density 0.066%

    No Known Activations