© 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. 3343
    Prev
    Next
    INDEX
    Explanations

    choosing specific items or data

    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
    SelectedItem
    -0.13
    olt
    -0.11
     selected
    -0.11
    _selected
    -0.10
    _selector
    -0.10
    ottom
    -0.10
    ItemSelected
    -0.10
    ILT
    -0.10
    Selected
    -0.10
    -selector
    -0.10
    POSITIVE LOGITS
    ivity
    0.25
    ively
    0.25
    eer
    0.18
    ors
    0.17
    ive
    0.17
     lá»įc
    0.16
    ividad
    0.15
    æĵ
    0.14
    SingleNode
    0.14
    eting
    0.13
    Activations Density 0.030%

    No Known Activations