© 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. 16-LLAMASCOPE-RES-32K
    11. 8841
    Prev
    Next
    INDEX
    Explanations

    language indicating caution or risk in future predictions

    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
    vie
    -0.15
    ents
    -0.14
    pcodes
    -0.14
    hb
    -0.14
    221
    -0.14
    afd
    -0.14
    921
    -0.14
    874
    -0.14
     recogn
    -0.14
    leen
    -0.14
    POSITIVE LOGITS
     Christoph
    0.14
     Heller
    0.14
    اÙħÙĩ
    0.14
     kuru
    0.14
    oge
    0.14
    IVA
    0.14
    nul
    0.13
    isky
    0.13
    ysi
    0.13
    apolis
    0.13
    Activations Density 0.074%

    No Known Activations