© 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. 14971
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to background checks and clearances

    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
    lew
    -0.15
    ;element
    -0.14
    emics
    -0.13
    ÑĥÑĩа
    -0.13
    ITT
    -0.13
    rix
    -0.13
    .weixin
    -0.13
     ЧаÑģ
    -0.13
    ieri
    -0.13
    igli
    -0.13
    POSITIVE LOGITS
     background
    0.49
     Background
    0.43
    background
    0.42
    Background
    0.40
     backgrounds
    0.39
    /background
    0.38
    -background
    0.38
    èĥĮæĻ¯
    0.36
     BACKGROUND
    0.35
    .background
    0.35
    Activations Density 0.045%

    No Known Activations