© 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. 2096
    Prev
    Next
    INDEX
    Explanations

    those early days

    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
     Already
    -0.11
     already
    -0.10
    Already
    -0.09
    already
    -0.09
     Previously
    -0.09
    kee
    -0.09
    _already
    -0.08
    æĹ¢
    -0.08
     å·²
    -0.08
    Æ¡n
    -0.08
    POSITIVE LOGITS
     initially
    0.80
     initial
    0.69
     early
    0.57
    initial
    0.56
    æľĢåĪĿ
    0.52
     Initially
    0.52
     inicial
    0.48
    Initially
    0.47
    early
    0.45
    åĪĿ
    0.44
    Activations Density 0.322%

    No Known Activations