© 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. 3-LLAMASCOPE-RES-32K
    11. 23338
    Prev
    Next
    INDEX
    Explanations

    instances of the word "yesterday."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erge
    -0.17
    .BLL
    -0.17
    说è¯Ŀ
    -0.16
    ERGE
    -0.14
    lier
    -0.14
    uts
    -0.14
    ily
    -0.14
     createContext
    -0.14
    uci
    -0.14
    .downcase
    -0.14
    POSITIVE LOGITS
    hte
    0.17
     Horton
    0.16
     Leakage
    0.16
    BlockSize
    0.15
    æĭĵ
    0.15
    lag
    0.15
    AntiForgeryToken
    0.14
    رÙĪج
    0.14
    ilight
    0.14
    reo
    0.14
    Activations Density 0.012%

    No Known Activations