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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65484
    Prev
    Next
    INDEX
    Explanations

    spatial position

    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
     along
    -0.14
    沿
    -0.12
     atop
    -0.11
    身ä¸Ĭ
    -0.10
    responseData
    -0.10
     Outside
    -0.10
    485
    -0.09
    èħ¹
    -0.09
     Eck
    -0.09
    stad
    -0.09
    POSITIVE LOGITS
     vedle
    0.32
     ÑĢÑıдом
    0.31
    æĹģ
    0.31
     beside
    0.30
     Bes
    0.29
     neben
    0.29
     side
    0.28
    Bes
    0.28
     next
    0.26
     lado
    0.24
    Activations Density 0.117%

    No Known Activations