© 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. 9274
    Prev
    Next
    INDEX
    Explanations

    specific noun phrases

    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
     -*-č\n
    -0.11
    įng
    -0.11
    ÅĻÃŃz
    -0.10
    eyim
    -0.09
    hsi
    -0.09
    apg
    -0.09
    ¨ë¶Ģ
    -0.09
    ******č\n
    -0.09
    .Dictionary
    -0.09
    kyt
    -0.09
    POSITIVE LOGITS
     system
    0.11
     aspect
    0.09
     Smy
    0.09
     IS
    0.08
     itself
    0.08
     neighb
    0.08
     process
    0.08
    osphere
    0.08
    nee
    0.08
     Bates
    0.08
    Activations Density 0.153%

    No Known Activations