© 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. 27887
    Prev
    Next
    INDEX
    Explanations

    origin or source

    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
     distant
    -0.12
    ระà¸ļà¸ļ
    -0.12
    รายà¸ģาร
    -0.12
    ระà¸Ķ
    -0.12
    รà¸ĸ
    -0.11
     à¤ĩसस
    -0.11
    ноÑģÑıÑĤ
    -0.10
    меÑĩ
    -0.10
    ระยะ
    -0.10
    รà¸Ńà¸ļ
    -0.10
    POSITIVE LOGITS
    /to
    0.26
    دÙĪاج
    0.19
     luego
    0.16
    ager
    0.16
    t
    0.16
     vá»±
    0.15
     scratch
    0.15
    ula
    0.15
    /about
    0.14
    m
    0.14
    Activations Density 0.127%

    No Known Activations