© 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. 23-LLAMASCOPE-RES-32K
    6. 31536
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and court cases

    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
    hind
    -0.18
    erdale
    -0.17
    łģ
    -0.16
    itar
    -0.15
    hong
    -0.15
    инов
    -0.15
    impse
    -0.15
     ç¯
    -0.15
    pector
    -0.14
    اÙĪÛĮ
    -0.14
    POSITIVE LOGITS
     Supreme
    0.52
     supreme
    0.42
     Court
    0.39
     highest
    0.39
    æľĢé«ĺ
    0.36
     Highest
    0.36
     High
    0.36
     higher
    0.34
    Sup
    0.32
    Court
    0.32
    Activations Density 0.103%

    No Known Activations