© 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. 16625
    Prev
    Next
    INDEX
    Explanations

    words starting with sub

    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
    scribe
    -0.13
    sip
    -0.10
     Vit
    -0.10
    uchs
    -0.09
    588
    -0.09
     vit
    -0.09
    overn
    -0.09
     subsidiary
    -0.09
    scription
    -0.09
    fy
    -0.09
    POSITIVE LOGITS
    lim
    0.15
    woo
    0.14
    zero
    0.13
    bing
    0.13
    mers
    0.13
    ito
    0.13
     sandwich
    0.12
    aÅŁÄ±
    0.12
    =sub
    0.12
    heading
    0.12
    Activations Density 0.024%

    No Known Activations