© 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. 31605
    Prev
    Next
    INDEX
    Explanations

    without a/an/la, then [noun]

    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
    (æľ¨
    -0.10
    ataka
    -0.10
     autob
    -0.10
     Magnus
    -0.09
     Cars
    -0.09
    utow
    -0.09
    perc
    -0.09
    orch
    -0.09
     Oprah
    -0.08
    irit
    -0.08
    POSITIVE LOGITS
     machine
    0.17
     machines
    0.15
     máy
    0.15
     chiếc
    0.14
     owning
    0.14
     equipment
    0.14
    à¹Ģà¸Ħร
    0.12
     machinery
    0.11
     borrowed
    0.11
     instrument
    0.11
    Activations Density 0.223%

    No Known Activations