© 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. 22562
    Prev
    Next
    INDEX
    Explanations

    changes in things

    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
    ors
    -0.09
    Unchecked
    -0.09
     prov
    -0.09
    _authenticated
    -0.09
    eded
    -0.09
    wert
    -0.08
    ponsible
    -0.08
    iram
    -0.08
    oup
    -0.08
    opleft
    -0.08
    POSITIVE LOGITS
    over
    0.15
    ยà¸Ļà¹ģà¸Ľà¸¥à¸ĩ
    0.12
     ownership
    0.12
    (changes
    0.11
     tack
    0.11
    ring
    0.11
     Hands
    0.10
    Ñĩив
    0.10
    amenti
    0.10
    Made
    0.10
    Activations Density 0.013%

    No Known Activations