© 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. 14717
    Prev
    Next
    INDEX
    Explanations

    process, procedure, processor

    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
     fe
    -0.09
     lo
    -0.09
     prov
    -0.09
    -than
    -0.09
    à¥įरà¤ļ
    -0.09
     tut
    -0.08
    ering
    -0.08
    nech
    -0.08
    ¢
    -0.08
     subst
    -0.08
    POSITIVE LOGITS
    надлеж
    0.13
    duct
    0.12
    blem
    0.12
    EDURE
    0.11
    obuf
    0.11
    essor
    0.11
    urement
    0.11
    gram
    0.10
    ject
    0.10
    allel
    0.10
    Activations Density 0.075%

    No Known Activations