© 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. 32282
    Prev
    Next
    INDEX
    Explanations

    various context items

    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
     climate
    -0.30
     Climate
    -0.26
    climate
    -0.24
     weather
    -0.23
    Climate
    -0.22
     klim
    -0.19
     climates
    -0.19
    weather
    -0.19
    .weather
    -0.19
     clim
    -0.18
    POSITIVE LOGITS
     pests
    0.10
    redo
    0.10
     pand
    0.09
    iquer
    0.09
    _UNICODE
    0.09
     nuclear
    0.09
     hod
    0.09
    èĻ«
    0.08
    kud
    0.08
    tvrt
    0.08
    Activations Density 0.062%

    No Known Activations