© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 8100
    Prev
    Next
    INDEX
    Explanations

    celcius and ever produced

    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
    Negative Logits
     metallic
    -0.12
     cement
    -0.12
     Metallic
    -0.11
     Cement
    -0.11
     concrete
    -0.11
     Op
    -0.11
     asphalt
    -0.11
     vol
    -0.10
     Concrete
    -0.10
     brick
    -0.10
    POSITIVE LOGITS
     cast
    0.16
     extr
    0.13
    casting
    0.13
    606
    0.13
    loys
    0.12
     sheet
    0.12
    werk
    0.12
    æŀIJ
    0.12
     werk
    0.12
     casting
    0.12
    Activations Density 0.034%

    No Known Activations