© 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. 34211
    Prev
    Next
    INDEX
    Explanations

    2000 words in chemical industry

    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
    _shuffle
    -0.10
     sanction
    -0.09
    amedi
    -0.09
    ë¹
    -0.09
     صاØŃ
    -0.08
     mbox
    -0.08
     Plot
    -0.08
    ứt
    -0.08
    ngo
    -0.08
    aments
    -0.08
    POSITIVE LOGITS
     mesh
    0.14
     Mesh
    0.12
     CAS
    0.12
    mesh
    0.11
    mg
    0.10
     Affairs
    0.10
     purity
    0.10
    loh
    0.09
     Ih
    0.09
     rall
    0.09
    Activations Density 0.067%

    No Known Activations