© 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. 38143
    Prev
    Next
    INDEX
    Explanations

    and/or technical terms

    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
     wr
    -0.10
    conc
    -0.09
    çĩ
    -0.09
     Brunswick
    -0.09
    ConfigurationException
    -0.09
    266
    -0.08
    issy
    -0.08
    ازÙĬ
    -0.08
    Ñĥй
    -0.08
     Whe
    -0.08
    POSITIVE LOGITS
    ä¹ī
    0.11
    utin
    0.10
    anes
    0.10
    linger
    0.09
    ustos
    0.09
    /******/
    0.09
    èĬĻ
    0.09
     gust
    0.09
    ials
    0.09
     Beard
    0.09
    Activations Density 0.118%

    No Known Activations