© 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. 20423
    Prev
    Next
    INDEX
    Explanations

    5p downregulated AD

    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
     Cancer
    -0.10
    utdown
    -0.09
    lashes
    -0.09
     cancer
    -0.09
     prol
    -0.09
     Jude
    -0.08
     developmental
    -0.08
     Checker
    -0.08
     Terra
    -0.08
     Weber
    -0.08
    POSITIVE LOGITS
     Alzheimer
    0.33
     amy
    0.28
     Amy
    0.25
    amy
    0.24
    Amy
    0.23
    zheimer
    0.22
     dementia
    0.22
     tau
    0.21
    ementia
    0.21
     memory
    0.19
    Activations Density 0.034%

    No Known Activations