© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 37651
    Prev
    Next
    INDEX
    Explanations

    numbers followed by specific words

    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
    azel
    -0.11
    ãĢĢr
    -0.11
     percentage
    -0.10
     slight
    -0.10
    apis
    -0.09
    Months
    -0.09
     Hazel
    -0.09
    azo
    -0.09
    âĢij
    -0.09
    Years
    -0.09
    POSITIVE LOGITS
    âĢ²
    0.16
    âĢ³
    0.15
    ths
    0.11
     åIJįåīį
    0.10
    'er
    0.10
    ContentSize
    0.10
    ners
    0.10
    -й
    0.09
    anı
    0.09
    iedo
    0.09
    Activations Density 0.131%

    No Known Activations