© 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. 44380
    Prev
    Next
    INDEX
    Explanations

    herbs and plants

    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
     pea
    -0.14
     Insecta
    -0.11
     botanical
    -0.11
     berry
    -0.10
    Cream
    -0.10
    ersions
    -0.10
    éra
    -0.09
     Ñıй
    -0.09
    鸣
    -0.09
     Floral
    -0.09
    POSITIVE LOGITS
     elder
    0.18
     verb
    0.16
     sage
    0.15
     mint
    0.15
     Elder
    0.14
     passion
    0.14
     hops
    0.14
     nast
    0.14
     hone
    0.14
     guar
    0.14
    Activations Density 0.096%

    No Known Activations