© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 33889
    Prev
    Next
    INDEX
    Explanations

    mi followed by verbs

    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
    ocl
    -0.10
     fitte
    -0.09
     siti
    -0.09
     pract
    -0.09
     Pep
    -0.09
     nos
    -0.09
     strav
    -0.09
    iat
    -0.09
    ξει
    -0.09
     lut
    -0.09
    POSITIVE LOGITS
    ASF
    0.10
    ANGO
    0.10
    .MixedReality
    0.10
     autoc
    0.10
     concent
    0.09
     bast
    0.09
    occ
    0.09
     gust
    0.09
    urge
    0.09
    ò
    0.09
    Activations Density 0.035%

    No Known Activations