© 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. 39284
    Prev
    Next
    INDEX
    Explanations

    invaluable resource

    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
    eel
    -0.11
    apiro
    -0.09
    inea
    -0.09
    _stub
    -0.09
     associates
    -0.08
     succinct
    -0.08
    .ColumnHeader
    -0.08
     bullet
    -0.08
    chap
    -0.08
    Backdrop
    -0.08
    POSITIVE LOGITS
     resource
    0.27
    resource
    0.24
     resources
    0.20
     useful
    0.20
    -resource
    0.19
    èµĦæºIJ
    0.19
     Resource
    0.19
    Resource
    0.18
     valuable
    0.18
    .resource
    0.17
    Activations Density 0.085%

    No Known Activations