© 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. 21236
    Prev
    Next
    INDEX
    Explanations

    talk to me about

    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
    ï¼´
    -0.10
    adors
    -0.10
     speech
    -0.10
     writ
    -0.09
    ISCO
    -0.09
     è¨Ģ
    -0.09
    hong
    -0.09
     OMIT
    -0.09
     verbal
    -0.09
     speakers
    -0.09
    POSITIVE LOGITS
     about
    0.15
     fork
    0.13
     normal
    0.12
     tentang
    0.11
     despre
    0.11
    about
    0.10
     accent
    0.10
     limp
    0.10
    /about
    0.09
    ative
    0.09
    Activations Density 0.107%

    No Known Activations