© 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. 21354
    Prev
    Next
    INDEX
    Explanations

    additional or other items/details

    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
     actual
    -0.11
     other
    -0.11
     Actual
    -0.10
    oda
    -0.10
     OTHER
    -0.10
    \tTokenName
    -0.10
     Kurum
    -0.10
     дÑĢÑĥгим
    -0.09
     mnemonic
    -0.09
    other
    -0.09
    POSITIVE LOGITS
     details
    0.20
     detail
    0.14
     relevant
    0.14
    details
    0.13
     Details
    0.13
     information
    0.12
     necessary
    0.12
    -than
    0.12
     features
    0.12
    Details
    0.12
    Activations Density 0.057%

    No Known Activations