© 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. 8842
    Prev
    Next
    INDEX
    Explanations

    anti-virus industry and names

    np_acts-logits-general · gemini-2.5-flash-lite

    underscores, particularly those used in placeholder names like "NAME_1" or "NAME_2".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
    enta
    -0.10
    FIXME
    -0.08
     Gum
    -0.08
     âĢª
    -0.08
    ümÃ¼ÅŁ
    -0.08
    ï¿
    -0.08
    rypton
    -0.07
     Pur
    -0.07
     Moy
    -0.07
    ีà¹Ģà¸Ń
    -0.07
    POSITIVE LOGITS
    pon
    0.08
    oru
    0.08
    andr
    0.07
    treeview
    0.07
     AnyObject
    0.07
     GLuint
    0.07
    arella
    0.07
     actionTypes
    0.07
    741
    0.07
     Gibbs
    0.07
    Activations Density 1.371%

    No Known Activations