© 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. 34413
    Prev
    Next
    INDEX
    Explanations

    prompt response and action

    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
    rien
    -0.09
     continued
    -0.09
    ongo
    -0.09
    defer
    -0.08
    ritz
    -0.08
     sid
    -0.08
    amik
    -0.08
     unt
    -0.08
    /TR
    -0.08
     impatient
    -0.08
    POSITIVE LOGITS
     acted
    0.33
     act
    0.29
     quick
    0.28
     action
    0.27
     acting
    0.26
     дейÑģÑĤв
    0.24
    åıįåºĶ
    0.22
     reaction
    0.22
     react
    0.21
    quick
    0.21
    Activations Density 0.087%

    No Known Activations