© 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. 34371
    Prev
    Next
    INDEX
    Explanations

    UMAP Uniform Manifold Approximation

    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
     åį
    -0.10
     bil
    -0.09
     vent
    -0.09
     DeV
    -0.09
    ully
    -0.09
     Psychic
    -0.09
     apex
    -0.09
     junk
    -0.09
    uhan
    -0.09
    aign
    -0.09
    POSITIVE LOGITS
     dbs
    0.14
     ag
    0.14
     DB
    0.14
     density
    0.14
     Vor
    0.13
    ç°
    0.12
     Noise
    0.12
     linkage
    0.12
     noise
    0.12
    å¯Ĩ
    0.12
    Activations Density 0.018%

    No Known Activations