© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 16-LLAMASCOPE-RES-32K
    6. 21100
    Prev
    Next
    INDEX
    Explanations

    references to Warren Buffett and investment opportunities related to General Electric

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antino
    -0.15
    etch
    -0.15
    allest
    -0.14
    emoc
    -0.14
    agini
    -0.14
    /function
    -0.14
    -solid
    -0.14
    /pm
    -0.14
    Agent
    -0.13
    beit
    -0.13
    POSITIVE LOGITS
    .jsoup
    0.17
     invest
    0.17
     investing
    0.17
     investment
    0.17
     Buffett
    0.17
     Berkshire
    0.16
    æ°Ĺãģ«åħ¥
    0.16
     acquiring
    0.15
    quist
    0.15
    abcdefghijkl
    0.15
    Activations Density 0.059%

    No Known Activations