© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 58370
    Prev
    Next
    INDEX
    Explanations

    phrases ending lists or sections

    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
    .scalablytyped
    -0.08
    ì¹Ń
    -0.08
    _TypeInfo
    -0.08
    ntax
    -0.08
    ÃĹ</
    -0.08
    ÅĽcie
    -0.07
    -č\n
    -0.07
     Erotische
    -0.07
    ernaut
    -0.07
    /Area
    -0.07
    POSITIVE LOGITS
    âĢħ
    0.10
     ìĹŃìĭľ
    0.07
     Zot
    0.07
    DataBase
    0.07
    ActionResult
    0.07
    ABCDEFG
    0.07
     agre
    0.07
    íĥĢìĿ´
    0.07
    женÑĮ
    0.07
    ìį¨
    0.07
    Activations Density 0.653%

    No Known Activations