© 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. 47144
    Prev
    Next
    INDEX
    Explanations

    immediate or instant effects

    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
     preceding
    -0.09
    Ahead
    -0.09
    uem
    -0.09
     Quickly
    -0.09
    afx
    -0.09
    Intialized
    -0.09
    oom
    -0.09
     hastily
    -0.09
    Indented
    -0.08
    Adjacent
    -0.08
    POSITIVE LOGITS
     immediate
    0.72
     immediately
    0.72
     immedi
    0.58
     sofort
    0.52
     Immediate
    0.49
     ÑģÑĢазÑĥ
    0.47
     instant
    0.45
    Immediate
    0.43
     Immediately
    0.43
     hemen
    0.41
    Activations Density 0.226%

    No Known Activations