© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 7935
    Prev
    Next
    INDEX
    Explanations

    Synthetizing, sorvetes, Niacet, civet

    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
    Negative Logits
    er
    -0.12
    ham
    -0.12
    houses
    -0.12
    y
    -0.12
    adero
    -0.12
    icum
    -0.11
    house
    -0.11
    spe
    -0.11
    ERS
    -0.11
    erable
    -0.11
    POSITIVE LOGITS
    ted
    0.25
    ters
    0.24
    ts
    0.20
    tes
    0.19
    ting
    0.17
    tt
    0.17
    ten
    0.15
    ta
    0.15
    tings
    0.15
    ty
    0.14
    Activations Density 0.133%

    No Known Activations