© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 34709
    Prev
    Next
    INDEX
    Explanations

    past continuation or progression

    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
    AndWait
    -0.09
    ango
    -0.08
     Fuse
    -0.08
    orr
    -0.08
    /********************************************************************************
    -0.08
     ï¾Ĭ
    -0.08
     then
    -0.07
     Birch
    -0.07
    CREMENT
    -0.07
     putas
    -0.07
    POSITIVE LOGITS
     still
    0.17
    still
    0.14
     continued
    0.13
     already
    0.13
     earlier
    0.13
     previous
    0.13
     continue
    0.13
     continuation
    0.12
    åĪļæīį
    0.12
     after
    0.12
    Activations Density 0.017%

    No Known Activations