© 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. 20696
    Prev
    Next
    INDEX
    Explanations

    look at, up, or for

    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
     inward
    -0.10
    åĪ°åºķ
    -0.09
     outward
    -0.09
    -､
    -0.09
    LocalizedMessage
    -0.08
     Coun
    -0.08
    ÃŁ
    -0.08
    obao
    -0.08
     بج
    -0.08
    dÄĽ
    -0.08
    POSITIVE LOGITS
     closely
    0.20
     at
    0.15
    ups
    0.15
    AndFeel
    0.12
    ie
    0.11
    è¦ĭ
    0.11
     thấy
    0.11
    heed
    0.11
    see
    0.11
    outs
    0.11
    Activations Density 0.023%

    No Known Activations