© 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. 44300
    Prev
    Next
    INDEX
    Explanations

    focuses on actions or purpose

    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
    immel
    -0.09
    ãģ«ãģ¯
    -0.09
    nell
    -0.08
     unrelated
    -0.08
    etto
    -0.08
    ubl
    -0.08
     aftermarket
    -0.08
     nackte
    -0.08
    opian
    -0.08
    imb
    -0.08
    POSITIVE LOGITS
     focus
    0.19
     focuses
    0.18
     targets
    0.17
    focus
    0.16
     deal
    0.16
     focused
    0.15
     pert
    0.15
     deals
    0.14
     cat
    0.14
     target
    0.14
    Activations Density 0.162%

    No Known Activations