Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65250
    Prev
    Next
    INDEX
    Explanations

    requesting copy or access

    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
    lops
    -0.12
    ãĥ
    -0.09
    ats
    -0.08
    ãĢĢãĥ¾
    -0.08
    PTY
    -0.08
     Hel
    -0.08
    ALER
    -0.08
    adem
    -0.08
    igi
    -0.08
     tri
    -0.08
    POSITIVE LOGITS
     copies
    0.39
     access
    0.34
     copy
    0.32
    copies
    0.29
     Copies
    0.27
    copy
    0.23
     acesso
    0.22
    access
    0.21
     acceso
    0.19
    Copy
    0.19
    Activations Density 0.160%

    No Known Activations