© 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. 27-LLAMASCOPE-RES-32K
    11. 5862
    Prev
    Next
    INDEX
    Explanations

    references to social inequality and issues related to discrimination and education

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    aign
    -0.19
    zel
    -0.16
    建设
    -0.14
     SUBSTITUTE
    -0.14
    æ±Ĥè´Ń
    -0.14
     Ø´ÙĪر
    -0.13
    æ½®
    -0.13
    agnostic
    -0.13
    imoto
    -0.13
     BRAND
    -0.13
    POSITIVE LOGITS
     inequality
    0.44
     ine
    0.42
     inequalities
    0.40
     unequal
    0.34
     equity
    0.34
     equality
    0.33
    ine
    0.31
     disparities
    0.30
     wealth
    0.30
    equality
    0.29
    Activations Density 0.361%

    No Known Activations