© 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. 32808
    Prev
    Next
    INDEX
    Explanations

    i had

    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
    Unnamed
    -0.09
     Holt
    -0.09
    Soup
    -0.09
    ipay
    -0.08
    833
    -0.08
     Garn
    -0.08
     Boyle
    -0.08
    ipeg
    -0.08
    MouseMove
    -0.08
     shall
    -0.08
    POSITIVE LOGITS
    å¿ħé¡»
    0.21
     cannot
    0.19
     must
    0.18
    ä¸įèĥ½
    0.18
     phải
    0.16
    ä¸įèĥ½ä¸ºç©º
    0.15
     Cannot
    0.14
    cannot
    0.14
     mus
    0.14
     trebuie
    0.13
    Activations Density 0.016%

    No Known Activations