© 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. 20622
    Prev
    Next
    INDEX
    Explanations

    references to cancer treatment and protocols

    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
    utra
    -0.17
    <Props
    -0.15
    æ
    -0.14
    ÑĢоÑİ
    -0.14
     snatch
    -0.14
    vfs
    -0.14
    ypress
    -0.14
    rouch
    -0.13
    Ú¯ÛĮ
    -0.13
    Toe
    -0.13
    POSITIVE LOGITS
     Cancer
    0.34
     chemotherapy
    0.33
     Radiation
    0.30
     cancer
    0.30
     tumor
    0.28
     radiation
    0.28
     tum
    0.27
     Onc
    0.26
     metast
    0.25
     cancers
    0.24
    Activations Density 0.105%

    No Known Activations