© 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. 27-LLAMASCOPE-RES-32K
    11. 18867
    Prev
    Next
    INDEX
    Explanations

    references to personal passions and the importance of doing what one loves

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecz
    -0.15
     Sure
    -0.15
    arendra
    -0.15
    fir
    -0.14
    ï½¥
    -0.14
    Impl
    -0.14
    forder
    -0.14
    apper
    -0.14
     actively
    -0.14
    acky
    -0.14
    POSITIVE LOGITS
     excel
    0.18
    .qq
    0.16
     pur
    0.15
    ؤ
    0.15
     set
    0.14
    ãģĵãģĿ
    0.14
    Ĵáŀ
    0.14
    è³£
    0.14
     Came
    0.14
     came
    0.14
    Activations Density 0.076%

    No Known Activations