© 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. 63177
    Prev
    Next
    INDEX
    Explanations

    capturing attention, keeping viewers watching

    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
    icken
    -0.09
     Impress
    -0.09
     torture
    -0.09
     distressed
    -0.09
    erva
    -0.09
     spare
    -0.08
     correctness
    -0.08
    iona
    -0.08
     inhibitors
    -0.08
     intimid
    -0.08
    POSITIVE LOGITS
     engagement
    0.32
     interest
    0.29
     hook
    0.28
     Engagement
    0.27
     engage
    0.26
     engaged
    0.25
     Interest
    0.24
     capt
    0.23
     Hook
    0.23
    engage
    0.23
    Activations Density 0.093%

    No Known Activations