© 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. 10024
    Prev
    Next
    INDEX
    Explanations

    references to military alliances and international relations involving the US

    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
     USA
    -0.51
    USA
    -0.47
     America
    -0.46
     america
    -0.42
     СШÐIJ
    -0.42
    America
    -0.41
     Americans
    -0.40
    ç¾İåĽ½
    -0.38
     Usa
    -0.38
     usa
    -0.37
    POSITIVE LOGITS
     European
    0.22
     Europeans
    0.21
     Europe
    0.21
     Canadian
    0.21
    Canadian
    0.20
     Canada
    0.20
    -European
    0.19
    .mx
    0.19
    Canada
    0.19
     europé
    0.18
    Activations Density 0.155%

    No Known Activations