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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33513
    Prev
    Next
    INDEX
    Explanations

    always be doing something

    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
     martyr
    -0.09
    hear
    -0.09
    ä¹ħ
    -0.09
    686
    -0.09
    ISTIC
    -0.09
    é¡ĺãģĦ
    -0.09
    deen
    -0.08
     hear
    -0.08
    znám
    -0.08
    GIS
    -0.08
    POSITIVE LOGITS
     surround
    0.12
     always
    0.12
    Always
    0.12
     Always
    0.12
     divers
    0.12
    always
    0.11
    çĽ¸ä¿¡
    0.11
     вÑģегда
    0.11
    ohana
    0.10
     ALWAYS
    0.10
    Activations Density 0.080%

    No Known Activations