© 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. 3203
    Prev
    Next
    INDEX
    Explanations

    true identity/meaning/essence

    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
    naire
    -0.10
    ese
    -0.09
    regor
    -0.09
    reur
    -0.09
    isel
    -0.08
     ãĢī
    -0.08
    /th
    -0.08
    sei
    -0.08
    lico
    -0.08
    ism
    -0.08
    POSITIVE LOGITS
     nature
    0.20
    st
    0.18
    /false
    0.18
     colors
    0.15
    -blue
    0.15
    /original
    0.14
     identity
    0.14
    -life
    0.14
     extent
    0.14
     Colors
    0.13
    Activations Density 0.017%

    No Known Activations