© 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. 29-LLAMASCOPE-RES-32K
    11. 21624
    Prev
    Next
    INDEX
    Explanations

    phrases indicating surprise or expectation

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    spect
    -0.15
    ãĥŃãĥ¼
    -0.15
    eyh
    -0.15
    -describedby
    -0.14
    onya
    -0.14
    KER
    -0.14
    IXEL
    -0.14
    iveau
    -0.14
    à¹Ģà¸Ļ
    -0.14
    lexport
    -0.14
    POSITIVE LOGITS
     sup
    0.22
     surprise
    0.19
     great
    0.18
     sur
    0.17
     unsur
    0.17
    .fig
    0.17
     complete
    0.16
    -sup
    0.16
     wonder
    0.16
     huge
    0.16
    Activations Density 0.015%

    No Known Activations