© 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. 16302
    Prev
    Next
    INDEX
    Explanations

    with intention or care

    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
     ÑģÑĤоÑĢон
    -0.12
     Reputation
    -0.09
     pled
    -0.08
     Ñģвоим
    -0.08
    446
    -0.08
    805
    -0.08
    ìį¨
    -0.08
    Directions
    -0.08
    é¾Ħ
    -0.08
    327
    -0.08
    POSITIVE LOGITS
     regard
    0.24
     consideration
    0.21
     regards
    0.20
     intent
    0.18
     intention
    0.17
     care
    0.17
     due
    0.16
    outh
    0.16
    standing
    0.15
     aim
    0.15
    Activations Density 0.057%

    No Known Activations