© 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. 12502
    Prev
    Next
    INDEX
    Explanations

    events and campaigns associated with health awareness, exhibitions, and celebrations

    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
    aylor
    -0.16
    ils
    -0.14
    Ïģή
    -0.14
    ecz
    -0.14
    çŃĭ
    -0.14
     Elliott
    -0.14
    iel
    -0.14
    irit
    -0.14
    èª
    -0.14
    _ASSUME
    -0.14
    POSITIVE LOGITS
     running
    0.67
     runs
    0.64
     Running
    0.57
    running
    0.57
     Runs
    0.54
     ran
    0.54
    Running
    0.53
    -running
    0.53
    runs
    0.50
     RUNNING
    0.50
    Activations Density 0.123%

    No Known Activations