Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 44896
    Prev
    Next
    INDEX
    Explanations

    alzheimer disease dementia

    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
    IDX
    -0.09
    âī§
    -0.09
    arrera
    -0.09
     asthma
    -0.08
    ERV
    -0.08
    Uvs
    -0.08
    aled
    -0.08
    FX
    -0.08
    ween
    -0.08
     constitution
    -0.08
    POSITIVE LOGITS
     Alzheimer
    0.26
     memory
    0.26
     Memory
    0.24
     dementia
    0.24
    ementia
    0.22
    Memory
    0.21
    memory
    0.19
    /memory
    0.19
    zheimer
    0.18
    -memory
    0.18
    Activations Density 0.048%

    No Known Activations