© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 36417
    Prev
    Next
    INDEX
    Explanations

    platform, tool, technique, solution, product

    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
    byn
    -0.09
    quires
    -0.08
    /animations
    -0.08
     obsahuje
    -0.08
    ùa
    -0.08
     assort
    -0.08
    /preferences
    -0.08
    includes
    -0.08
     Contains
    -0.08
     zig
    -0.08
    POSITIVE LOGITS
    çĶ¨äºİ
    0.23
     used
    0.22
    used
    0.18
     designed
    0.16
    Used
    0.16
     Used
    0.15
     purpose
    0.15
     meant
    0.14
     intended
    0.14
     çĶ¨
    0.12
    Activations Density 0.267%

    No Known Activations