© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43578
    Prev
    Next
    INDEX
    Explanations

    the synthesis, ability, laws, production

    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
     fundraising
    -0.09
    afone
    -0.09
    BOOLE
    -0.09
    rawer
    -0.08
    nde
    -0.08
    OUN
    -0.08
    cheid
    -0.08
    adic
    -0.08
     ApiResponse
    -0.08
    ¶Į
    -0.08
    POSITIVE LOGITS
     ones
    0.38
    ones
    0.23
     following
    0.19
     ability
    0.18
     Ones
    0.17
     likes
    0.17
     aforementioned
    0.15
    ONES
    0.14
     follows
    0.14
     obvious
    0.14
    Activations Density 0.094%

    No Known Activations