© 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. 18320
    Prev
    Next
    INDEX
    Explanations

    expressing interest

    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
     å¿
    -0.10
    ï¿£
    -0.09
     Igor
    -0.09
    ãĤ¿ãĥ«
    -0.09
    uto
    -0.09
    652
    -0.09
    709
    -0.08
    YK
    -0.08
    439
    -0.08
    _traits
    -0.08
    POSITIVE LOGITS
     interest
    0.72
     Interest
    0.60
    interest
    0.55
    Interest
    0.55
     interested
    0.53
     interests
    0.52
     инÑĤеÑĢеÑģ
    0.48
     interesse
    0.47
     interes
    0.47
    interested
    0.43
    Activations Density 0.118%

    No Known Activations