© 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. 18302
    Prev
    Next
    INDEX
    Explanations

    seeds to germinate

    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
     Recon
    -0.12
     drip
    -0.11
     precip
    -0.10
     concent
    -0.10
    asti
    -0.09
     bug
    -0.09
    U
    -0.09
     recon
    -0.09
    ateur
    -0.09
     Sentry
    -0.09
    POSITIVE LOGITS
     ger
    0.41
     Ger
    0.32
    Ger
    0.28
    ger
    0.21
     GER
    0.21
     spr
    0.19
     strat
    0.19
    GER
    0.18
     scar
    0.17
     viability
    0.17
    Activations Density 0.052%

    No Known Activations