© 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. 10-LLAMASCOPE-RES-32K
    11. 3385
    Prev
    Next
    INDEX
    Explanations

    references to products, particularly in the context of retail or online marketplaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dealloc
    -0.15
    breadcrumb
    -0.15
    anager
    -0.14
    yal
    -0.13
     dán
    -0.13
    ats
    -0.13
    -ts
    -0.13
    angible
    -0.13
     Tac
    -0.13
    edar
    -0.13
    POSITIVE LOGITS
    asan
    0.14
     Cle
    0.13
    agner
    0.13
    .localized
    0.13
    CLE
    0.13
     Manifest
    0.13
    eyen
    0.13
    ylie
    0.13
    ê·¸ëŁ¬
    0.12
    NullException
    0.12
    Activations Density 2.472%

    No Known Activations