© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 26-LLAMASCOPE-RES-32K
    11. 7781
    Prev
    Next
    INDEX
    Explanations

    references to sewing and crafts, particularly involving embroidery techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shelf
    -0.15
    éijij
    -0.15
    oze
    -0.15
     Sessions
    -0.14
     Foreign
    -0.14
    elere
    -0.14
    faction
    -0.14
    ãĤĤãĤĬ
    -0.14
    ắm
    -0.14
    _MINOR
    -0.14
    POSITIVE LOGITS
     Sew
    0.30
     sewing
    0.29
     sew
    0.29
     stitches
    0.28
     stitch
    0.25
     Singer
    0.25
     Stitch
    0.22
     sewer
    0.22
     seam
    0.21
     hem
    0.21
    Activations Density 0.009%

    No Known Activations