© 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. 22-LLAMASCOPE-RES-32K
    11. 3319
    Prev
    Next
    INDEX
    Explanations

    references to automation and its impact on jobs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    foy
    -0.14
    azzo
    -0.14
    uhe
    -0.14
    éĹª
    -0.14
    ÙİÙģ
    -0.14
    .unlock
    -0.13
     Dann
    -0.13
     Shooter
    -0.13
     Silence
    -0.13
    .ISupportInitialize
    -0.13
    POSITIVE LOGITS
     jobs
    0.30
     robots
    0.28
     job
    0.28
     Automation
    0.27
     robot
    0.27
     machines
    0.27
     automation
    0.26
     Jobs
    0.25
     Machines
    0.25
    .robot
    0.25
    Activations Density 0.110%

    No Known Activations