© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 18562
    Prev
    Next
    INDEX
    Explanations

    out my, me the

    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
    Negative Logits
     pian
    -0.11
    isco
    -0.10
    vid
    -0.09
     suites
    -0.09
    aur
    -0.09
    ippet
    -0.09
    avern
    -0.08
     Swords
    -0.08
     sword
    -0.08
    styleType
    -0.08
    POSITIVE LOGITS
     nearby
    0.12
     pair
    0.12
     handful
    0.12
     stool
    0.11
    hold
    0.11
     tissues
    0.11
    éĹ²
    0.10
    /vue
    0.10
     fallen
    0.10
    ä¸Ģåį·
    0.10
    Activations Density 0.049%

    No Known Activations