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. 44786
    Prev
    Next
    INDEX
    Explanations

    sentence endings followed by location

    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
     Surround
    -0.13
     surrounded
    -0.11
    æĺ¯æĪij
    -0.10
    iferay
    -0.09
    ´Ī
    -0.09
    [in
    -0.09
    âĢIJ'
    -0.09
    afil
    -0.09
    oes
    -0.09
    ãĢĢï¾ŀ
    -0.09
    POSITIVE LOGITS
     there
    0.17
     opposite
    0.14
    There
    0.12
    there
    0.12
     ÑģÑĢеди
    0.12
    Among
    0.12
    aped
    0.12
     There
    0.12
     center
    0.12
     Direct
    0.11
    Activations Density 0.087%

    No Known Activations