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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-32K
    11. 20036
    Prev
    Next
    INDEX
    Explanations

    references to systems, frameworks, and organized entities in the context of societal structures and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ubu
    -0.14
    ัวหà¸Ļ
    -0.14
    ultan
    -0.14
    Ø¡
    -0.14
    =<?=
    -0.14
    ValueCollection
    -0.14
    icina
    -0.13
    fur
    -0.13
    DATED
    -0.13
    anz
    -0.13
    POSITIVE LOGITS
     themselves
    0.17
    abo
    0.15
    olas
    0.14
    bell
    0.14
    iler
    0.14
     mies
    0.13
    ãĥ¼ãĥĬ
    0.13
    ünchen
    0.13
    ashire
    0.13
    ÑĪли
    0.13
    Activations Density 0.225%

    No Known Activations