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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 63349
    Prev
    Next
    INDEX
    Explanations

    beautiful beaches and scenery

    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
     shoreline
    -0.11
     Shore
    -0.10
     inland
    -0.10
     mainland
    -0.10
    æĭ¿
    -0.09
    é±
    -0.09
    brook
    -0.08
    опол
    -0.08
     seaside
    -0.08
    ÅĻÃŃm
    -0.08
    POSITIVE LOGITS
     beaches
    0.27
     beach
    0.24
     sands
    0.19
     плÑı
    0.19
     Beach
    0.18
     plage
    0.17
     strand
    0.17
     lif
    0.17
     sand
    0.15
    æ²Ļ
    0.15
    Activations Density 0.046%

    No Known Activations