© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 2701
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to legal or formal agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    riere
    -0.15
    gart
    -0.13
    GINE
    -0.13
    ujet
    -0.13
    CustomAttributes
    -0.12
    ospace
    -0.12
    Ìģ
    -0.12
    å®ŀåľ¨
    -0.12
    ÙĪÛĮÙĩ
    -0.12
     Mate
    -0.12
    POSITIVE LOGITS
     Holmes
    0.15
     poil
    0.13
     bdsm
    0.13
     quoi
    0.13
    ÎŃÏģ
    0.13
    .Native
    0.13
    idor
    0.12
    chg
    0.12
     McCl
    0.12
    mÃŃ
    0.12
    Activations Density 0.283%

    No Known Activations