© 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
    5. 50-RESID-POST-GF
    7. 33899
    Prev
    Next
    INDEX
    Explanations

    say yes

    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
     konkrét
    -0.09
    apus
    -0.08
    ÃĹ\n\n
    -0.08
    itsu
    -0.08
    æ¤į
    -0.08
    BOOT
    -0.08
    éric
    -0.08
     Walton
    -0.08
    untu
    -0.08
    xes
    -0.08
    POSITIVE LOGITS
     yes
    0.23
     Yes
    0.21
    yes
    0.18
    Yes
    0.18
     YES
    0.18
    YES
    0.15
     anything
    0.15
     oui
    0.14
    _yes
    0.13
    anything
    0.13
    Activations Density 0.024%

    No Known Activations