© 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. 24-LLAMASCOPE-RES-32K
    11. 10023
    Prev
    Next
    INDEX
    Explanations

    terms related to sanctions and regulatory measures against governments or regimes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     inorder
    -0.15
    éľ²
    -0.14
    _ABI
    -0.14
     tolerate
    -0.14
    WSC
    -0.13
    hai
    -0.13
    pered
    -0.13
    conte
    -0.13
    ãĥ¥
    -0.13
    squ
    -0.13
    POSITIVE LOGITS
     sanctions
    0.42
     embargo
    0.29
     sanction
    0.27
     penalties
    0.26
     freezes
    0.23
    ban
    0.23
     freezing
    0.22
    san
    0.22
     froze
    0.21
     ban
    0.21
    Activations Density 0.061%

    No Known Activations