© 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. 12961
    Prev
    Next
    INDEX
    Explanations

    script, instruction, action, step, weight, model

    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
    InstanceOf
    -0.08
    olg
    -0.08
     reb
    -0.08
     rencontrer
    -0.07
     McDon
    -0.07
     ãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢãĢĢ
    -0.07
    ekil
    -0.07
     troubled
    -0.07
    OrElse
    -0.07
    Closure
    -0.07
    POSITIVE LOGITS
     Tal
    0.09
     gamle
    0.08
     again
    0.08
    698
    0.08
     Hass
    0.08
    kea
    0.08
    achu
    0.08
    804
    0.08
    ''"
    0.08
    neck
    0.08
    Activations Density 0.308%

    No Known Activations