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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 34018
    Prev
    Next
    INDEX
    Explanations

    decentralized domain name system

    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
     crypto
    -0.10
     Griffin
    -0.10
     Brid
    -0.09
     Krish
    -0.09
     unh
    -0.09
     Carr
    -0.09
    IL
    -0.09
     Homer
    -0.09
    ve
    -0.09
    aci
    -0.09
    POSITIVE LOGITS
    è¯ļ
    0.12
     POW
    0.11
     mer
    0.11
     honest
    0.10
     Mer
    0.10
    azaar
    0.10
    _pow
    0.10
    å¡ļ
    0.10
     SHA
    0.09
    ì¦Ŀ
    0.09
    Activations Density 0.022%

    No Known Activations