© 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. 64036
    Prev
    Next
    INDEX
    Explanations

    expressing interest in

    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
     Pruitt
    -0.09
    ertz
    -0.09
    анов
    -0.09
    áng
    -0.09
    clusive
    -0.08
    elop
    -0.08
     Bunny
    -0.08
    èIJ¥ä¸ļ
    -0.08
    edly
    -0.08
    irl
    -0.08
    POSITIVE LOGITS
    ly
    0.14
    .scalablytyped
    0.13
     parties
    0.12
    interested
    0.12
     interested
    0.11
    idata
    0.11
     interest
    0.10
    /lic
    0.10
     Interest
    0.10
    ested
    0.09
    Activations Density 0.016%

    No Known Activations