© 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. 16921
    Prev
    Next
    INDEX
    Explanations

    provide responses

    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
     köln
    -0.07
    GridColumn
    -0.07
     sorte
    -0.07
    HERE
    -0.07
    оба
    -0.07
    noinspection
    -0.07
    AppDelegate
    -0.07
    ereal
    -0.07
     ($('#
    -0.07
    âĹĭ
    -0.07
    POSITIVE LOGITS
    ëį°ìĿ´íĬ¸
    0.09
    ESSAGES
    0.09
    Intialized
    0.08
    eniable
    0.08
    #
    0.08
    URLException
    0.08
     ^{°}
    0.07
    IVEN
    0.07
     addCriterion
    0.07
    ìĸ
    0.07
    Activations Density 0.724%

    No Known Activations