© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 14025
    Prev
    Next
    INDEX
    Explanations

    above or previous

    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
     downstairs
    -0.24
     lowercase
    -0.19
    åºķ
    -0.18
     lows
    -0.18
     below
    -0.18
    .toLowerCase
    -0.16
     ниже
    -0.16
    ä¸ĭ
    -0.16
     bottoms
    -0.16
     lowest
    -0.15
    POSITIVE LOGITS
     upper
    0.47
    upper
    0.38
     higher
    0.35
     Upper
    0.34
     above
    0.32
     веÑĢÑħ
    0.32
    Upper
    0.32
     Above
    0.30
    ä¸Ĭ
    0.29
    higher
    0.29
    Activations Density 0.160%

    No Known Activations