© 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. 26-LLAMASCOPE-RES-32K
    11. 31560
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ratulations
    -0.22
    ãĥ£
    -0.21
    ãĥ¥
    -0.17
    ãĤ§
    -0.15
    دÙĪاج
    -0.15
    ÑģÑĤÑİ
    -0.14
     thá»ĥ
    -0.14
    ÛĢ
    -0.14
     vá»įng
    -0.14
    ÑģÑĤÑĮ
    -0.13
    POSITIVE LOGITS
    s
    1.85
    Ùĩ
    0.82
    ska
    0.80
    sburg
    0.73
    sik
    0.71
    sak
    0.69
    ÏĤ
    0.68
    sar
    0.68
    sian
    0.65
    sand
    0.65
    Activations Density 2.058%

    No Known Activations