© 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. 27581
    Prev
    Next
    INDEX
    Explanations

    those affected by

    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
    lâm
    -0.10
     Berm
    -0.10
     жен
    -0.09
    hots
    -0.09
     Womens
    -0.09
    itom
    -0.09
    ijke
    -0.09
     trú
    -0.09
     Enemies
    -0.09
     genders
    -0.08
    POSITIVE LOGITS
     persons
    0.39
     individuals
    0.35
     people
    0.35
     person
    0.25
     Persons
    0.25
     personnes
    0.25
    persons
    0.25
    Persons
    0.24
     patients
    0.24
    people
    0.23
    Activations Density 0.158%

    No Known Activations