© 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. 16-LLAMASCOPE-RES-32K
    11. 10224
    Prev
    Next
    INDEX
    Explanations

    significant changes or events in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    .mx
    -0.16
    ivot
    -0.15
    rello
    -0.15
    aterangepicker
    -0.15
    nte
    -0.15
    .hw
    -0.15
    aliz
    -0.14
    atro
    -0.14
    ifax
    -0.14
    ymax
    -0.14
    POSITIVE LOGITS
     rect
    0.27
     remedy
    0.22
     remed
    0.21
     now
    0.20
     Rect
    0.20
     ìĿ´ìłľ
    0.18
    now
    0.18
    _now
    0.18
    Rect
    0.18
    rect
    0.17
    Activations Density 0.171%

    No Known Activations