© 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. 17490
    Prev
    Next
    INDEX
    Explanations

    to you or to suck

    np_acts-logits-general · gemini-2.5-flash-lite

    dismissive phrases in quoted dialogue that minimize someone's feelings or tell them to toughen up.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
     neither
    -0.12
     arguably
    -0.09
     actually
    -0.09
     Pret
    -0.09
     Cer
    -0.09
     desp
    -0.09
     pret
    -0.09
    UP
    -0.09
     Worldwide
    -0.09
     merc
    -0.08
    POSITIVE LOGITS
     therefore
    0.11
     pÅĻece
    0.10
     Ñıк
    0.10
     XYZ
    0.10
    739
    0.10
     SUCH
    0.09
    rible
    0.09
     victim
    0.09
     surely
    0.09
     xyz
    0.09
    Activations Density 0.201%

    No Known Activations