© 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. 42728
    Prev
    Next
    INDEX
    Explanations

    letter from, He had

    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
    Iss
    -0.10
     ç©
    -0.09
    สำ
    -0.09
     emailing
    -0.08
     Conversation
    -0.08
     تÙĦÙģ
    -0.08
    aaS
    -0.08
     telegram
    -0.08
     ç¤
    -0.08
    ì¤Ģ
    -0.08
    POSITIVE LOGITS
     message
    0.17
     addressed
    0.14
     unsigned
    0.14
     crypt
    0.14
     sender
    0.13
     enclosed
    0.12
     read
    0.12
    unsigned
    0.12
    message
    0.12
     signed
    0.11
    Activations Density 0.071%

    No Known Activations