© 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. 3030
    Prev
    Next
    INDEX
    Explanations

    cognitive dissonance

    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
     ambigu
    -0.12
     ambiguity
    -0.12
     Duy
    -0.10
     ambiguous
    -0.10
     faults
    -0.10
    MV
    -0.09
     inconsistency
    -0.09
     weakness
    -0.09
     divisive
    -0.09
     variability
    -0.09
    POSITIVE LOGITS
    Mismatch
    0.38
     mismatch
    0.35
    ismatch
    0.34
     difference
    0.33
    å·®
    0.29
    difference
    0.27
    discord
    0.26
    ISMATCH
    0.25
     discord
    0.25
    disconnect
    0.25
    Activations Density 0.204%

    No Known Activations