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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 23-LLAMASCOPE-RES-32K
    6. 11695
    Prev
    Next
    INDEX
    Explanations

    phrases related to Alzheimer's disease and cognitive decline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     neon
    -0.16
    Desktop
    -0.15
    754
    -0.15
    ISO
    -0.14
    éĺ
    -0.14
    座
    -0.14
     Neon
    -0.14
    /desktop
    -0.14
     ces
    -0.14
    desktop
    -0.14
    POSITIVE LOGITS
     Alzheimer
    0.52
     dementia
    0.47
    ementia
    0.40
     memory
    0.38
     Memory
    0.36
    memory
    0.34
    zheimer
    0.33
    Memory
    0.32
    .memory
    0.32
     forget
    0.31
    Activations Density 0.085%

    No Known Activations