© 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. 15111
    Prev
    Next
    INDEX
    Explanations

    instances of the word "despite" and its variations, indicating a focus on contrasting situations or unexpected outcomes

    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
    neh
    -0.15
    nees
    -0.15
    bps
    -0.14
    ERGE
    -0.14
    اÙħا
    -0.14
    atters
    -0.14
    eson
    -0.13
    ystack
    -0.13
    ollectors
    -0.13
    ëijĺ
    -0.13
    POSITIVE LOGITS
     being
    0.33
    being
    0.26
     having
    0.26
     Being
    0.23
    Being
    0.22
     obvious
    0.20
     occasional
    0.20
     knowing
    0.20
     efforts
    0.20
     contrary
    0.20
    Activations Density 0.033%

    No Known Activations