© 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. 30-LLAMASCOPE-RES-32K
    11. 17932
    Prev
    Next
    INDEX
    Explanations

    phrases related to the discussion of sugar and its effects on food and health

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Scaler
    -0.15
    ToDevice
    -0.14
     Salmon
    -0.14
     Salisbury
    -0.14
    Serializer
    -0.14
    essen
    -0.14
    owl
    -0.14
    readcr
    -0.14
    ashboard
    -0.13
    557
    -0.13
    POSITIVE LOGITS
     sugar
    0.68
     Sugar
    0.57
    Sugar
    0.52
     sugars
    0.50
     cane
    0.47
     sug
    0.45
     glucose
    0.45
    ç³ĸ
    0.44
     Sug
    0.41
     suc
    0.40
    Activations Density 0.042%

    No Known Activations