© 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. 57672
    Prev
    Next
    INDEX
    Explanations

    allows us to interact; when someone experiences; help people

    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
     Female
    -0.12
     femin
    -0.09
     Quint
    -0.09
    female
    -0.09
    Female
    -0.09
     colleague
    -0.09
    ÏĦαι
    -0.09
     female
    -0.09
    arsers
    -0.09
    zin
    -0.08
    POSITIVE LOGITS
     individuals
    0.40
     people
    0.33
    人们
    0.29
     Individuals
    0.29
    ä¸Ģ个人
    0.27
     humans
    0.24
    people
    0.23
     Ñĩеловек
    0.23
    人ãģ¯
    0.23
     ourselves
    0.23
    Activations Density 0.356%

    No Known Activations