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. 44857
    Prev
    Next
    INDEX
    Explanations

    with a focus or team

    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
    hei
    -0.10
     legend
    -0.09
     Dome
    -0.08
    ogi
    -0.08
    arya
    -0.08
    اÙĪØ±
    -0.08
    対
    -0.08
    activex
    -0.08
    typings
    -0.08
    asi
    -0.08
    POSITIVE LOGITS
     its
    0.23
     Its
    0.17
     regard
    0.17
    drawing
    0.16
     roots
    0.16
    Its
    0.16
     years
    0.15
    åħ¶
    0.15
    holding
    0.14
     regards
    0.14
    Activations Density 0.018%

    No Known Activations