© 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. 759
    Prev
    Next
    INDEX
    Explanations

    in this case

    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
    InProgress
    -0.11
    -IN
    -0.10
    anna
    -0.09
    iele
    -0.09
    åı²
    -0.08
    -in
    -0.08
    idas
    -0.08
    ongo
    -0.08
     damit
    -0.08
    435
    -0.08
    POSITIVE LOGITS
     here
    0.23
     neste
    0.21
    è¿ĻéĩĮ
    0.19
    here
    0.18
     здеÑģÑĮ
    0.18
     aquÃŃ
    0.18
     ìĿ´ë²Ī
    0.17
     burada
    0.17
     اÛĮÙĨجا
    0.17
     ìĹ¬ê¸°
    0.16
    Activations Density 0.155%

    No Known Activations