© 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. 60843
    Prev
    Next
    INDEX
    Explanations

    concessive clauses or statements of possibility

    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
    kus
    -0.10
    lok
    -0.10
     Caldwell
    -0.09
    arse
    -0.09
    ادر
    -0.09
    urent
    -0.09
    _rx
    -0.09
     athe
    -0.09
    оÑĤи
    -0.09
    arks
    -0.08
    POSITIVE LOGITS
     zwar
    0.28
     sice
    0.22
    èĻ½
    0.22
    èĻ½çĦ¶
    0.21
     may
    0.20
    iswa
    0.18
    may
    0.18
    Granted
    0.17
     może
    0.16
     maybe
    0.16
    Activations Density 0.124%

    No Known Activations