© 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. 30408
    Prev
    Next
    INDEX
    Explanations

    adaptable, adaptive, adaptability

    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
    ales
    -0.11
    ongan
    -0.10
    ''"
    -0.09
     hã
    -0.09
    รà¸ĵ
    -0.09
    clid
    -0.09
    kes
    -0.09
    eza
    -0.09
    _excerpt
    -0.09
    nier
    -0.09
    POSITIVE LOGITS
    ively
    0.24
    ability
    0.17
    ions
    0.17
    ation
    0.15
    ting
    0.14
    ative
    0.13
    ations
    0.13
    ive
    0.13
    ts
    0.12
    působ
    0.12
    Activations Density 0.013%

    No Known Activations