© 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. 43514
    Prev
    Next
    INDEX
    Explanations

    recognize and see

    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
     scenario
    -0.11
     scenarios
    -0.11
     vign
    -0.10
    Scenario
    -0.10
     Scenario
    -0.10
     acting
    -0.10
    ahkan
    -0.10
     Harr
    -0.10
    scenario
    -0.09
     breathable
    -0.09
    POSITIVE LOGITS
     photos
    0.18
     pictures
    0.17
     photographs
    0.17
    çħ§çīĩ
    0.16
     close
    0.15
     viewed
    0.14
    photos
    0.14
     descriptions
    0.13
     fotos
    0.13
     closely
    0.12
    Activations Density 0.131%

    No Known Activations