© 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. 2-LLAMASCOPE-RES-32K
    11. 2123
    Prev
    Next
    INDEX
    Explanations

    the word "because" and its variations to identify reasoning or justification in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    符
    -0.17
    omnia
    -0.16
     Moran
    -0.14
    -Sah
    -0.14
    ewart
    -0.14
    ailed
    -0.14
    imenti
    -0.14
    ples
    -0.14
     Sle
    -0.14
     åº
    -0.13
    POSITIVE LOGITS
    upo
    0.16
    аÑĢÑĩ
    0.16
    uni
    0.15
    usra
    0.15
    ilk
    0.14
    eton
    0.14
    retry
    0.14
    erno
    0.13
    reet
    0.13
    ania
    0.13
    Activations Density 0.042%

    No Known Activations