© 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. 49094
    Prev
    Next
    INDEX
    Explanations

    demo and trial

    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
     Twe
    -0.11
    Attempting
    -0.09
     attempting
    -0.09
     rag
    -0.09
    ULO
    -0.08
     interv
    -0.08
     RAND
    -0.08
    íĶ½
    -0.08
     Trick
    -0.08
     interviewing
    -0.08
    POSITIVE LOGITS
     trial
    0.35
     test
    0.31
     Trial
    0.26
     demo
    0.26
     trials
    0.25
     sample
    0.24
    trial
    0.23
     demonstration
    0.23
    Trial
    0.22
     samples
    0.20
    Activations Density 0.085%

    No Known Activations