© 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. 29175
    Prev
    Next
    INDEX
    Explanations

    was created or introduced

    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
     pÅĻitom
    -0.09
     covert
    -0.09
     Horton
    -0.08
     converted
    -0.08
     valide
    -0.08
    acons
    -0.08
    ilece
    -0.08
    HD
    -0.07
    otten
    -0.07
    >Welcome
    -0.07
    POSITIVE LOGITS
    emode
    0.10
    ohl
    0.10
    åħģ
    0.09
     allow
    0.09
     Dahl
    0.09
    SENS
    0.09
     basically
    0.09
     allows
    0.09
    istical
    0.09
    allow
    0.09
    Activations Density 0.048%

    No Known Activations