© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 20645
    Prev
    Next
    INDEX
    Explanations

    positive feedback about customer service and quality of work

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    .DataTable
    -0.14
     YOUR
    -0.14
    HasBeen
    -0.14
     HERE
    -0.13
    licative
    -0.13
    emand
    -0.13
    á»ijng
    -0.13
     rewarding
    -0.13
     NOTICE
    -0.13
     comfy
    -0.13
    POSITIVE LOGITS
    ç»ĻæĪij
    0.17
    让æĪij
    0.16
     meu
    0.14
    arie
    0.14
     meinen
    0.14
    ZO
    0.14
     communications
    0.14
     my
    0.14
     communication
    0.14
    esser
    0.14
    Activations Density 0.150%

    No Known Activations