© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 58721
    Prev
    Next
    INDEX
    Explanations

    contextual nouns

    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
    536
    -0.10
    BackPressed
    -0.09
    deniz
    -0.09
    548
    -0.09
    ãĥ¼ãĥį
    -0.09
    etz
    -0.09
    .Shapes
    -0.09
    Others
    -0.08
    ãģªãģ®
    -0.08
    Touchable
    -0.08
    POSITIVE LOGITS
     communities
    0.19
     things
    0.16
     people
    0.16
     societies
    0.15
     places
    0.15
     environments
    0.15
     companies
    0.13
     entities
    0.13
     situations
    0.13
     decisions
    0.12
    Activations Density 0.098%

    No Known Activations