© 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. 20682
    Prev
    Next
    INDEX
    Explanations

    references to culinary topics or the culinary arts

    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
    kaz
    -0.14
    æ´¾
    -0.14
    engu
    -0.14
     illeg
    -0.13
     Abdel
    -0.13
     Baz
    -0.13
     Freder
    -0.13
     Late
    -0.13
    pulse
    -0.13
    raud
    -0.13
    POSITIVE LOGITS
     cul
    0.28
     Cul
    0.24
    inary
    0.21
    minating
    0.20
    prit
    0.18
    cul
    0.18
    vier
    0.18
    INARY
    0.18
    ottes
    0.17
    ulative
    0.16
    Activations Density 0.008%

    No Known Activations