© 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. 7-LLAMASCOPE-RES-32K
    11. 1516
    Prev
    Next
    INDEX
    Explanations

    phrases related to pairing or complementing items, particularly in the context of food or accessories

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Aviv
    -0.16
    agar
    -0.16
    جا
    -0.16
    Ïĥε
    -0.14
    лиÑĩ
    -0.14
    llu
    -0.14
    ross
    -0.14
     Hao
    -0.14
    luv
    -0.14
    597
    -0.14
    POSITIVE LOGITS
     accompany
    0.17
    ymes
    0.17
     accompanying
    0.17
    æIJŃ
    0.16
    pert
    0.15
    imus
    0.15
     Chunk
    0.15
     accompanies
    0.15
     chunk
    0.14
    achel
    0.14
    Activations Density 0.059%

    No Known Activations