© 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. 17227
    Prev
    Next
    INDEX
    Explanations

    forms of 'to be' followed by -ing verbs

    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
    982
    -0.09
    arkan
    -0.09
     Holl
    -0.09
     Intern
    -0.09
     being
    -0.09
    thag
    -0.09
    394
    -0.09
    ï½Ŀ
    -0.09
    iske
    -0.08
     Hills
    -0.08
    POSITIVE LOGITS
     sure
    0.14
    ady
    0.11
    deal
    0.11
     dealing
    0.11
     targeting
    0.10
     tyr
    0.10
     deal
    0.10
     ÑĥвеÑĢ
    0.09
    åĽº
    0.09
    使çĶ¨
    0.09
    Activations Density 0.088%

    No Known Activations