© 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. 35348
    Prev
    Next
    INDEX
    Explanations

    use the `isinstance()` or AWS Identity

    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
     Gust
    -0.10
     Setter
    -0.09
    urge
    -0.09
     Bever
    -0.09
    anter
    -0.09
    ä»ģ
    -0.09
    ë
    -0.09
    avis
    -0.08
    HH
    -0.08
    assen
    -0.08
    POSITIVE LOGITS
     intros
    0.18
     meta
    0.17
     metadata
    0.17
    intros
    0.17
     INFORMATION
    0.16
    meta
    0.16
    metadata
    0.16
     information
    0.15
    information
    0.15
     glGet
    0.15
    Activations Density 0.152%

    No Known Activations