Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44963
    Prev
    Next
    INDEX
    Explanations

    March 18; Italian; course; essere

    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
     pornô
    -0.11
     بÙĪØ§Ø¨Ø©
    -0.10
    anship
    -0.10
     en
    -0.09
     bel
    -0.09
    olumn
    -0.09
     fragment
    -0.09
     Rhe
    -0.09
     follando
    -0.09
     na
    -0.09
    POSITIVE LOGITS
    ì
    0.14
    ù
    0.12
    ò
    0.11
     specular
    0.11
    Ãł
    0.11
    izzazione
    0.11
    òn
    0.10
    è
    0.10
    azione
    0.10
     Italian
    0.10
    Activations Density 0.004%

    No Known Activations