© 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. 34293
    Prev
    Next
    INDEX
    Explanations

    ultimate beach babe look

    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
     winters
    -0.15
    night
    -0.12
     snowy
    -0.12
     skiing
    -0.11
    rain
    -0.11
     night
    -0.11
     rains
    -0.11
     rainy
    -0.10
     Rain
    -0.10
     warming
    -0.10
    POSITIVE LOGITS
     summer
    0.35
     beach
    0.33
     Summer
    0.31
    Summer
    0.28
    summer
    0.27
     summ
    0.27
    å¤ı
    0.27
     Beach
    0.24
     sun
    0.23
     SUM
    0.23
    Activations Density 0.106%

    No Known Activations