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

    Neuronpedia

    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. 22-LLAMASCOPE-RES-32K
    11. 17654
    Prev
    Next
    INDEX
    Explanations

    references to antiques and vintage items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Convenience
    -0.16
     convenience
    -0.15
    .scalablytyped
    -0.15
    hire
    -0.15
     ä½IJ
    -0.14
    PKG
    -0.14
     Handy
    -0.14
    ูà¹Ī
    -0.14
     Tube
    -0.14
    ÄĻp
    -0.14
    POSITIVE LOGITS
     antique
    0.35
     Antique
    0.32
     ant
    0.32
     antiqu
    0.30
     vintage
    0.28
     auctions
    0.28
     auction
    0.28
     Auction
    0.27
     collectors
    0.27
     Ant
    0.26
    Activations Density 0.175%

    No Known Activations