© 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. 36133
    Prev
    Next
    INDEX
    Explanations

    drive formatting and copying

    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
    (Display
    -0.10
     Nab
    -0.10
    zo
    -0.10
    isse
    -0.10
    SSI
    -0.09
     interpol
    -0.09
     Earth
    -0.09
     Mich
    -0.09
    cdn
    -0.09
     Marvin
    -0.09
    POSITIVE LOGITS
     drive
    0.17
     letter
    0.14
     FAT
    0.14
    .format
    0.14
    letter
    0.13
     LETTER
    0.13
     Letter
    0.13
    drive
    0.13
     formatted
    0.12
    Fat
    0.12
    Activations Density 0.036%

    No Known Activations