© 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. 5303
    Prev
    Next
    INDEX
    Explanations

    words ending in certain suffixes

    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
    ening
    -0.12
    iability
    -0.09
    y
    -0.09
    bie
    -0.09
     Bern
    -0.08
    ariat
    -0.08
    lessness
    -0.08
    ened
    -0.08
    ign
    -0.08
    isable
    -0.08
    POSITIVE LOGITS
    (sp
    0.18
    ous
    0.12
     Alv
    0.10
    punkt
    0.10
    ymous
    0.10
    جا
    0.09
    iyet
    0.09
     Canter
    0.09
     vitae
    0.08
    dzi
    0.08
    Activations Density 0.242%

    No Known Activations