© 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. 26104
    Prev
    Next
    INDEX
    Explanations

    Instead, In, According

    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
    hei
    -0.11
    “;He
    -0.09
     ká»ĥ
    -0.09
    cimal
    -0.09
    heel
    -0.09
     styl
    -0.09
    IgnoreCase
    -0.09
    "He
    -0.09
     haul
    -0.08
     Persistence
    -0.08
    POSITIVE LOGITS
     according
    0.25
    ä»ĸ
    0.23
     ông
    0.23
     According
    0.23
     he
    0.22
     à¤īसन
    0.22
     ê·¸ëĬĶ
    0.21
     ä»ĸ
    0.21
    according
    0.19
    According
    0.19
    Activations Density 0.076%

    No Known Activations