© 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. 33630
    Prev
    Next
    INDEX
    Explanations

    meaning and significance of various conditions

    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
     reasons
    -0.09
    ouns
    -0.09
     manner
    -0.09
     vault
    -0.09
    èm
    -0.09
    iddet
    -0.09
    --+
    -0.08
    amed
    -0.08
    facts
    -0.08
     Reasons
    -0.08
    POSITIVE LOGITS
     meaning
    0.18
     purpose
    0.17
     bearing
    0.17
     significance
    0.16
     counterpart
    0.16
     effect
    0.15
     impact
    0.14
     appeal
    0.14
     value
    0.14
     component
    0.13
    Activations Density 0.158%

    No Known Activations