© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 9106
    Prev
    Next
    INDEX
    Explanations

    discovery and learning outcomes

    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
     Larson
    -0.09
     assured
    -0.09
     Bere
    -0.09
     Sonuç
    -0.09
     Beste
    -0.09
    ãĥ©ãĤ¯
    -0.09
    idente
    -0.09
     seeing
    -0.08
     seen
    -0.08
     sight
    -0.08
    POSITIVE LOGITS
     discover
    0.46
     discovered
    0.43
     discovers
    0.42
    åıijçİ°
    0.40
     discovery
    0.37
     learn
    0.37
    discover
    0.36
     learns
    0.36
     Discover
    0.35
     discovering
    0.35
    Activations Density 0.098%

    No Known Activations