© 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. 9886
    Prev
    Next
    INDEX
    Explanations

    pe or pec words

    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
     apparent
    -0.11
    preneur
    -0.10
     Reyn
    -0.10
    IONS
    -0.09
     nond
    -0.09
     Neutral
    -0.09
     Hv
    -0.09
    iller
    -0.08
    adden
    -0.08
     Rosenberg
    -0.08
    POSITIVE LOGITS
    uliar
    0.18
    (pe
    0.15
    formance
    0.13
    haps
    0.12
    .pe
    0.11
    .Pe
    0.11
    antry
    0.11
     pev
    0.11
     pe
    0.11
    ople
    0.11
    Activations Density 0.044%

    No Known Activations