© 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. 31-LLAMASCOPE-RES-32K
    11. 13795
    Prev
    Next
    INDEX
    Explanations

    phrases that involve comparisons and contrasts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    quam
    -0.14
    меÑĤÑĮ
    -0.13
    ëŀ
    -0.13
    ENDOR
    -0.13
    azi
    -0.13
     intric
    -0.12
    pivot
    -0.12
    REFERRED
    -0.12
     ÐĿай
    -0.12
    BeginInit
    -0.12
    POSITIVE LOGITS
     conservative
    0.23
     respectable
    0.23
     ballpark
    0.22
     peanuts
    0.22
     higher
    0.21
     equivalent
    0.21
     astronomical
    0.20
     enough
    0.20
     comparable
    0.20
     conserv
    0.20
    Activations Density 0.245%

    No Known Activations