© 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. 25180
    Prev
    Next
    INDEX
    Explanations

    quantifiers and extent adjectives

    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
     cá»±c
    -0.10
    極
    -0.10
     gaz
    -0.09
    æĽ´åĬł
    -0.09
    æŀģ
    -0.09
     недел
    -0.09
     overwhelming
    -0.09
    ono
    -0.09
     longest
    -0.09
     less
    -0.08
    POSITIVE LOGITS
     significant
    0.31
     quite
    0.29
     fairly
    0.26
     substantial
    0.25
     considerable
    0.24
     khá
    0.23
     знаÑĩ
    0.23
    stantial
    0.23
     decent
    0.23
    缸å½ĵ
    0.23
    Activations Density 0.231%

    No Known Activations