© 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. 62984
    Prev
    Next
    INDEX
    Explanations

    its weights

    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
    .preview
    -0.10
    iks
    -0.10
    996
    -0.10
    ople
    -0.09
     preprocessing
    -0.09
     Brady
    -0.09
     preview
    -0.09
    preview
    -0.09
     obl
    -0.09
    arget
    -0.09
    POSITIVE LOGITS
     weights
    0.24
     model
    0.21
     saved
    0.21
     save
    0.19
     Saved
    0.19
    Weights
    0.18
    weights
    0.18
     saving
    0.18
     weight
    0.17
     trained
    0.17
    Activations Density 0.065%

    No Known Activations