© 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. 21447
    Prev
    Next
    INDEX
    Explanations

    harmony

    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
    illard
    -0.10
    ardi
    -0.10
    ugu
    -0.09
    ty
    -0.09
    uring
    -0.09
    gy
    -0.09
    riot
    -0.09
    otine
    -0.09
    UAL
    -0.08
    inish
    -0.08
    POSITIVE LOGITS
    ious
    0.20
    iously
    0.17
    IOUS
    0.14
    icas
    0.11
    ics
    0.11
     harmon
    0.11
     discord
    0.11
    discord
    0.10
    har
    0.10
     harmony
    0.10
    Activations Density 0.024%

    No Known Activations