© 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. 27169
    Prev
    Next
    INDEX
    Explanations

    verbs like have, likes, visits

    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
     udál
    -0.09
    лиÑĪком
    -0.09
    }elseif
    -0.09
     наÑĩинаеÑĤ
    -0.08
    lesen
    -0.08
    ERVE
    -0.08
     æĸ¼
    -0.08
     shalt
    -0.08
    edia
    -0.08
     AIDS
    -0.08
    POSITIVE LOGITS
     have
    0.14
     adalah
    0.14
     бÑĭÑĤÑĮ
    0.13
     memiliki
    0.13
     être
    0.12
     är
    0.12
     είναι
    0.12
     být
    0.12
    æĺ¯
    0.12
     having
    0.12
    Activations Density 0.290%

    No Known Activations