© 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. 13836
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters, particularly in structured formats like code or mathematical equations

    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
    ullo
    -0.17
    elli
    -0.16
    eldorf
    -0.16
    68
    -0.16
    657
    -0.15
    678
    -0.15
    157
    -0.15
     TED
    -0.15
    770
    -0.15
    uede
    -0.15
    POSITIVE LOGITS
    0.26
    	    ↵
    0.25
    	   ↵
    0.23
     Liver
    0.22
    Liver
    0.21
    0.19
     Voj
    0.19
     liver
    0.19
    	  ↵
    0.19
    0.18
    Activations Density 0.049%

    No Known Activations