© 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. 38229
    Prev
    Next
    INDEX
    Explanations

    spam or scam content

    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
    pedia
    -0.14
    ively
    -0.12
    bilt
    -0.12
    ered
    -0.12
    اÙĨ
    -0.11
    paper
    -0.11
    ariat
    -0.11
    enment
    -0.11
    esel
    -0.11
    mente
    -0.11
    POSITIVE LOGITS
    ming
    0.44
    mer
    0.34
    med
    0.30
    my
    0.25
    mers
    0.24
    MING
    0.24
    ms
    0.18
    mys
    0.18
    bers
    0.18
    me
    0.17
    Activations Density 0.062%

    No Known Activations