© 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. 36222
    Prev
    Next
    INDEX
    Explanations

    holding or carrying

    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
     fingert
    -0.10
    inges
    -0.10
    blr
    -0.10
    iese
    -0.10
    æĬķ
    -0.10
    ullet
    -0.09
     Isles
    -0.09
    iesel
    -0.09
     handwriting
    -0.09
     pian
    -0.09
    POSITIVE LOGITS
     scept
    0.14
     bunch
    0.14
     hold
    0.14
     bouquet
    0.14
    hold
    0.13
     shopping
    0.13
     steering
    0.13
     holding
    0.13
     clipboard
    0.12
     reins
    0.12
    Activations Density 0.054%

    No Known Activations