© 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. 40871
    Prev
    Next
    INDEX
    Explanations

    friendly and helpful

    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
     diligent
    -0.11
    vier
    -0.11
    âĶ´
    -0.10
    ÙĪÙĬر
    -0.09
    :::::|
    -0.08
    reesome
    -0.08
    NodeType
    -0.08
    ResponseStatus
    -0.08
    ThanOr
    -0.08
    olar
    -0.08
    POSITIVE LOGITS
     friendly
    0.33
     nice
    0.31
     polit
    0.29
    riendly
    0.28
    friendly
    0.28
     Nice
    0.28
     nic
    0.27
     cord
    0.27
    -friendly
    0.26
    Nice
    0.25
    Activations Density 0.246%

    No Known Activations