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. 65425
    Prev
    Next
    INDEX
    Explanations

    hidden obstacles and surroundings

    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
     Daw
    -0.10
     driveway
    -0.09
     bare
    -0.09
    awah
    -0.09
     Roads
    -0.09
    åºŃ
    -0.09
     Seeds
    -0.09
     Dove
    -0.08
     proportions
    -0.08
     sky
    -0.08
    POSITIVE LOGITS
     bushes
    0.24
     bush
    0.21
     shadows
    0.16
     shr
    0.16
     кÑĥÑģÑĤ
    0.16
     nearby
    0.14
     brush
    0.14
     hedge
    0.14
     foliage
    0.14
     trees
    0.14
    Activations Density 0.055%

    No Known Activations