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. 45016
    Prev
    Next
    INDEX
    Explanations

    and none or not

    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
    ITTE
    -0.09
    ãĤ¤ãĤº
    -0.09
    airo
    -0.09
    _inches
    -0.09
    ogan
    -0.09
    кÑĢÑĭ
    -0.09
    taÅŁ
    -0.09
     alist
    -0.09
    usk
    -0.08
     Authentic
    -0.08
    POSITIVE LOGITS
     intended
    0.17
     meant
    0.15
     shouldn
    0.14
    缮çļĦ
    0.12
     entertainment
    0.12
    sole
    0.12
     disclaimer
    0.12
     purpose
    0.11
     not
    0.11
     neither
    0.11
    Activations Density 0.095%

    No Known Activations