© 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. 8-LLAMASCOPE-RES-32K
    11. 17131
    Prev
    Next
    INDEX
    Explanations

    comparisons or distinctions between different entities or concepts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     bow
    -0.15
    defgroup
    -0.15
    addtogroup
    -0.15
    agy
    -0.14
    emean
    -0.14
    bower
    -0.14
    Æ°á»Ľ
    -0.14
    Scala
    -0.14
    à¤Łà¤ķ
    -0.14
     fluid
    -0.14
    POSITIVE LOGITS
    IVATE
    0.16
    onta
    0.15
    ť
    0.15
     manned
    0.15
     Hal
    0.14
     Overse
    0.14
    aver
    0.14
    olla
    0.14
    avers
    0.14
    orth
    0.13
    Activations Density 0.280%

    No Known Activations