© 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. 39966
    Prev
    Next
    INDEX
    Explanations

    , followed by action 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
    ä½łä»¬
    -0.22
     yourselves
    -0.20
     Yours
    -0.13
     ìŬ룬ë¶Ħ
    -0.13
    ÙĥÙħ
    -0.12
     usted
    -0.12
     euch
    -0.11
    Seleccione
    -0.11
     themselves
    -0.11
     desea
    -0.10
    POSITIVE LOGITS
     kannst
    0.22
     ÑĤебе
    0.21
     ÏĥοÏħ
    0.21
     jsi
    0.21
     ÑĤебÑı
    0.21
     tu
    0.20
     thy
    0.19
     Tu
    0.18
     puedes
    0.17
     te
    0.17
    Activations Density 0.218%

    No Known Activations