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. 44846
    Prev
    Next
    INDEX
    Explanations

    Palace, nerves, antibiotic

    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
     à¹Ĩ
    -0.09
    alia
    -0.08
    ,、
    -0.08
    Ymd
    -0.08
    haar
    -0.08
    lfw
    -0.08
    GNUC
    -0.08
    leet
    -0.08
     ëĦ¤ìĿ´íĬ¸
    -0.08
     JFactory
    -0.08
    POSITIVE LOGITS
    (sp
    0.19
    @gmail
    0.13
    /-
    0.10
    ceae
    0.10
    .com
    0.09
     ​​
    0.09
    ​
    0.09
    elry
    0.09
    ritten
    0.09
    MimeType
    0.08
    Activations Density 0.442%

    No Known Activations