© 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. 21504
    Prev
    Next
    INDEX
    Explanations

    explicit scenarios or requests

    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
     convict
    -0.09
    ese
    -0.09
     Porno
    -0.09
     appropri
    -0.09
     cla
    -0.08
     interfer
    -0.08
     nab
    -0.08
     trunc
    -0.08
     Sha
    -0.08
    CM
    -0.08
    POSITIVE LOGITS
     darkness
    0.11
    çĬ¯ç½ª
    0.11
    atever
    0.10
     DARK
    0.10
     darker
    0.10
    åĪº
    0.09
    _dark
    0.09
     Sick
    0.09
     Darkness
    0.09
    éĤª
    0.09
    Activations Density 0.083%

    No Known Activations