© 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. 36238
    Prev
    Next
    INDEX
    Explanations

    other NLP tasks

    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
     physical
    -0.11
    Physical
    -0.11
     untranslated
    -0.10
     bif
    -0.10
     plural
    -0.10
     Physical
    -0.10
     pronunciation
    -0.10
    _HW
    -0.10
    TransparentColor
    -0.09
     histor
    -0.09
    POSITIVE LOGITS
     text
    0.21
     language
    0.18
     Language
    0.18
    æĸĩ
    0.17
     communications
    0.17
     speech
    0.16
    _text
    0.16
     communication
    0.15
     Communications
    0.15
     Communication
    0.15
    Activations Density 0.313%

    No Known Activations