© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44399
    Prev
    Next
    INDEX
    Explanations

    discovery or absurd event

    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
    OUCH
    -0.10
    彡
    -0.09
     видно
    -0.08
     superiority
    -0.08
    §è¡Į
    -0.08
     confessed
    -0.08
     ç±
    -0.08
     supremacy
    -0.08
    éģĬ
    -0.08
     RELEASE
    -0.08
    POSITIVE LOGITS
     discovery
    0.74
     Discovery
    0.57
    åıijçİ°
    0.55
     discover
    0.53
     discovered
    0.51
    Discovery
    0.50
     discoveries
    0.50
     discovering
    0.47
     discovers
    0.45
     Discover
    0.44
    Activations Density 0.143%

    No Known Activations