© 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. 29026
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thr" in various forms and contexts, suggesting it focuses on themes of thrashing, thrill, or related actions

    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
    ements
    -0.16
    æĻ´
    -0.16
     gal
    -0.16
    holders
    -0.15
    ogan
    -0.15
    eti
    -0.14
    370
    -0.14
    els
    -0.14
    eya
    -0.14
    ogo
    -0.14
    POSITIVE LOGITS
    fare
    0.17
    bounce
    0.15
     ÙħشاÙĩدة
    0.15
    anter
    0.14
    \Modules
    0.14
    ToUpper
    0.14
    ваÑĢ
    0.14
     Haram
    0.14
    445
    0.13
    ASF
    0.13
    Activations Density 0.009%

    No Known Activations