© 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. 18258
    Prev
    Next
    INDEX
    Explanations

    conversion event

    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
     inbound
    -0.11
     Roths
    -0.11
     outbound
    -0.10
     Pine
    -0.09
    å¸Ĥåł´
    -0.09
    advert
    -0.09
     neglig
    -0.09
     Cumhur
    -0.08
     repe
    -0.08
    лаж
    -0.08
    POSITIVE LOGITS
     conversion
    0.25
     Conversion
    0.24
    Conversion
    0.23
     conversions
    0.21
     leads
    0.21
    conversion
    0.20
     lead
    0.18
     Leads
    0.18
     Lead
    0.17
     Convert
    0.17
    Activations Density 0.050%

    No Known Activations