© 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. 901
    Prev
    Next
    INDEX
    Explanations

    required cleanup actions

    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
     ÑĢазÑĢеÑĪ
    -0.10
     dequeue
    -0.09
    ieve
    -0.09
    ertia
    -0.09
    _delegate
    -0.09
     Rig
    -0.09
     Pok
    -0.08
    |/
    -0.08
     democr
    -0.08
     maneu
    -0.08
    POSITIVE LOGITS
     releasing
    0.21
     GC
    0.19
     resources
    0.18
     Release
    0.18
     release
    0.18
     released
    0.17
     destruction
    0.17
    éĩĬ
    0.17
    æŀIJ
    0.17
     releases
    0.16
    Activations Density 0.040%

    No Known Activations