© 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. 44260
    Prev
    Next
    INDEX
    Explanations

    positive and formal tone

    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
     unint
    -0.10
    ÑĽ
    -0.09
     rápido
    -0.09
     downright
    -0.08
     grandes
    -0.08
    ãģ£ãģ
    -0.08
    ntl
    -0.08
    591
    -0.08
     необ
    -0.08
     erót
    -0.08
    POSITIVE LOGITS
     ÏĢοÏħ
    0.10
     yang
    0.09
    assin
    0.08
     velit
    0.08
    orage
    0.08
    plnÄĽ
    0.08
     иÑģполн
    0.08
     trò
    0.08
     somewhat
    0.08
    è½
    0.08
    Activations Density 0.095%

    No Known Activations