© 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. 9849
    Prev
    Next
    INDEX
    Explanations

    tourist attractions and sights

    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
    aptor
    -0.10
     Camping
    -0.10
     camps
    -0.08
    eldorf
    -0.08
     camping
    -0.08
    _ASSUME
    -0.08
    lette
    -0.08
     æ®
    -0.08
    croft
    -0.08
    .ButterKnife
    -0.08
    POSITIVE LOGITS
     sights
    0.40
     attractions
    0.39
     sight
    0.38
     attraction
    0.34
    attr
    0.34
     Attr
    0.32
    Attr
    0.32
     Sight
    0.28
     tourist
    0.28
     landmarks
    0.27
    Activations Density 0.109%

    No Known Activations