© 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. 28925
    Prev
    Next
    INDEX
    Explanations

    AI expressing neutrality

    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
    _parm
    -0.09
     disposable
    -0.09
    vern
    -0.09
     ><?
    -0.09
     invers
    -0.09
    ingu
    -0.09
     Harden
    -0.09
    豪
    -0.08
     Nikol
    -0.08
    _inverse
    -0.08
    POSITIVE LOGITS
     neutral
    0.81
     Neutral
    0.71
     neutrality
    0.67
    Neutral
    0.66
    neutral
    0.66
    -neutral
    0.61
     neutr
    0.59
     neut
    0.50
     impartial
    0.47
     ней
    0.43
    Activations Density 0.286%

    No Known Activations