© 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. 25-LLAMASCOPE-RES-32K
    11. 15103
    Prev
    Next
    INDEX
    Explanations

    references to Charles Darwin and his work

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    tte
    -0.17
    gers
    -0.16
    ih
    -0.15
    erties
    -0.15
    ander
    -0.15
    å¹ķ
    -0.14
    ihan
    -0.14
    embr
    -0.14
    amento
    -0.14
    ihat
    -0.14
    POSITIVE LOGITS
    lington
    0.22
    ÃŃo
    0.22
    win
    0.21
    lings
    0.21
    lene
    0.20
    ë¹
    0.20
    Dar
    0.20
    shan
    0.19
    erca
    0.19
    fur
    0.19
    Activations Density 0.013%

    No Known Activations