© 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. 39115
    Prev
    Next
    INDEX
    Explanations

    always

    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
    istrovstvÃŃ
    -0.10
    Anywhere
    -0.10
    orget
    -0.09
     BOTH
    -0.09
    /*č\n
    -0.09
    ัà¸ĩà¹Ħม
    -0.09
    ovÄĽ
    -0.09
     EVERY
    -0.09
    ILLE
    -0.09
    ừa
    -0.08
    POSITIVE LOGITS
     always
    0.72
    always
    0.60
     sempre
    0.59
     siempre
    0.58
     toujours
    0.57
     вÑģегда
    0.55
     Always
    0.55
    Always
    0.52
     vždy
    0.49
     luôn
    0.48
    Activations Density 0.211%

    No Known Activations