© 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. 21-LLAMASCOPE-RES-32K
    11. 20771
    Prev
    Next
    INDEX
    Explanations

    phrases related to accidents and fatal incidents

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ingleton
    -0.18
    åĤ·
    -0.17
    rens
    -0.15
    伤
    -0.15
    죽
    -0.14
    elah
    -0.14
    ãĥŃãĥ¼
    -0.14
    .Restr
    -0.14
    urance
    -0.14
     sublic
    -0.14
    POSITIVE LOGITS
     falling
    0.22
     lightning
    0.20
     tree
    0.19
     Lightning
    0.17
     truck
    0.16
     train
    0.16
     rogue
    0.16
     stray
    0.16
     Falling
    0.15
     fallen
    0.15
    Activations Density 0.149%

    No Known Activations