© 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. 37461
    Prev
    Next
    INDEX
    Explanations

    empirical studies and meta-analyses

    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
     Briggs
    -0.09
     ÄĮech
    -0.09
     correlation
    -0.09
     observ
    -0.09
     Qed
    -0.09
     Opport
    -0.09
    DF
    -0.09
    AccessType
    -0.09
     campaigning
    -0.09
     Yao
    -0.09
    POSITIVE LOGITS
     meta
    0.16
    APA
    0.13
     findings
    0.13
    ERP
    0.13
     APA
    0.12
    meta
    0.12
    Meta
    0.12
    é¼
    0.12
     Baron
    0.12
     Meta
    0.12
    Activations Density 0.123%

    No Known Activations