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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 20-LLAMASCOPE-RES-32K
    11. 15596
    Prev
    Next
    INDEX
    Explanations

    phrases related to business practices and liability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erna
    -0.15
    ().'/
    -0.15
    002
    -0.14
    inde
    -0.13
    ÑĦоÑĢ
    -0.13
    ï¼Ŀ
    -0.13
    .lu
    -0.13
    ision
    -0.13
    iams
    -0.13
     ابتد
    -0.13
    POSITIVE LOGITS
     finally
    0.99
     Finally
    0.86
     Lastly
    0.85
    Lastly
    0.84
    finally
    0.82
    Finally
    0.81
     final
    0.57
    	finally
    0.57
    æľĢåIJİ
    0.54
     third
    0.53
    Activations Density 0.457%

    No Known Activations