© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35058
    Prev
    Next
    INDEX
    Explanations

    assistant response marker

    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
     Patri
    -0.08
    r
    -0.08
    ìĿ´ì§Ģ
    -0.07
     Consortium
    -0.07
     needle
    -0.07
    /
    -0.07
    '
    -0.07
    487
    -0.07
     |=
    -0.07
    -automatic
    -0.07
    POSITIVE LOGITS
    ©©
    0.09
    ]int
    0.09
    ̣
    0.09
    ÐĴÑĤ
    0.09
    /Foundation
    0.08
     initComponents
    0.08
    egin
    0.08
    .IsNullOr
    0.08
    getRepository
    0.08
    .wp
    0.08
    Activations Density 0.164%

    No Known Activations