© 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. 46800
    Prev
    Next
    INDEX
    Explanations

    to bring, not reciprocate, don't give, can't quite put, he found

    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
     Dover
    -0.09
    366
    -0.09
     recess
    -0.09
     Stub
    -0.09
    inde
    -0.08
    etat
    -0.08
    specifier
    -0.08
    ovky
    -0.08
     exhaustive
    -0.08
    à¹ģล
    -0.08
    POSITIVE LOGITS
     until
    0.16
     nerve
    0.13
    until
    0.13
     seriously
    0.13
    .until
    0.11
    æķ¢
    0.11
     bisher
    0.11
     recip
    0.10
     admit
    0.10
     anything
    0.10
    Activations Density 0.040%

    No Known Activations