© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38779
    Prev
    Next
    INDEX
    Explanations

    are the same

    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
    .parents
    -0.10
    ering
    -0.10
     tranqu
    -0.10
     perfor
    -0.09
     vocal
    -0.09
     finger
    -0.09
     taller
    -0.09
    ess
    -0.09
     backbone
    -0.09
     viv
    -0.09
    POSITIVE LOGITS
     assets
    0.13
     asset
    0.12
    -assets
    0.10
    asset
    0.10
    оÑĢаз
    0.10
     Assets
    0.10
     Asset
    0.10
     symmetry
    0.10
    âĮĴ
    0.09
    ocha
    0.09
    Activations Density 0.089%

    No Known Activations