© 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. 8630
    Prev
    Next
    INDEX
    Explanations

    more advanced features

    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
    ijkstra
    -0.09
    .mi
    -0.09
    adam
    -0.09
     Dillon
    -0.09
    ãĥ¾
    -0.08
     particulars
    -0.08
     aspect
    -0.08
    è²
    -0.08
    owitz
    -0.08
    alem
    -0.08
    POSITIVE LOGITS
     features
    0.45
    features
    0.38
     Features
    0.38
    Features
    0.34
     feature
    0.29
     FEATURES
    0.29
    _features
    0.29
    .features
    0.27
    (features
    0.26
     advanced
    0.24
    Activations Density 0.119%

    No Known Activations