© 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 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. 25-LLAMASCOPE-RES-32K
    11. 20889
    Prev
    Next
    INDEX
    Explanations

    concepts related to workplace productivity, employee satisfaction, and client relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anymore
    -0.16
    âĢ¦↵
    -0.14
    ën
    -0.14
     pomocÃŃ
    -0.14
    lasses
    -0.14
     ÑĩÑĤобÑĭ
    -0.14
    :first
    -0.14
     still
    -0.13
     recently
    -0.13
     completely
    -0.13
    POSITIVE LOGITS
     overall
    0.28
    overall
    0.24
     ultimately
    0.23
     later
    0.22
     downstream
    0.20
    ä¹ĥ
    0.20
     Ultimately
    0.19
     Overall
    0.19
     indirectly
    0.17
    Overall
    0.17
    Activations Density 0.438%

    No Known Activations