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. 45023
    Prev
    Next
    INDEX
    Explanations

    commonly known as

    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
     dubbed
    -0.13
     termed
    -0.10
     named
    -0.10
    490
    -0.10
     Named
    -0.10
     tant
    -0.09
     dub
    -0.09
     terminology
    -0.09
     name
    -0.09
    imir
    -0.09
    POSITIVE LOGITS
     simply
    0.24
    ç®Ģ
    0.23
     اختص
    0.23
    缩
    0.21
     kurz
    0.21
     Ñģок
    0.21
     short
    0.20
     ì¤Ħ
    0.20
     kıs
    0.19
    縮
    0.19
    Activations Density 0.212%

    No Known Activations