© 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. 37595
    Prev
    Next
    INDEX
    Explanations

    code output explanations

    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
     gor
    -0.10
     fore
    -0.09
     spotting
    -0.09
     Garcia
    -0.09
    ubs
    -0.09
     stro
    -0.09
     âĹĦ
    -0.08
     ro
    -0.08
     Eleanor
    -0.08
     cr
    -0.08
    POSITIVE LOGITS
    output
    0.12
     output
    0.12
    -output
    0.11
    Output
    0.11
     Output
    0.10
    spb
    0.10
    è¾ĵåĩº
    0.10
     vlas
    0.09
    `\n
    0.09
    ç»ĵæŀľ
    0.09
    Activations Density 0.003%

    No Known Activations