© 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. 9-LLAMASCOPE-RES-32K
    11. 10108
    Prev
    Next
    INDEX
    Explanations

    references to specific people or entities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ÑĦеÑĢ
    -0.16
    andr
    -0.15
    zz
    -0.15
    yun
    -0.15
    geois
    -0.15
    ắp
    -0.15
    ler
    -0.14
    itution
    -0.14
    ظ
    -0.14
    LER
    -0.14
    POSITIVE LOGITS
     Wyatt
    0.16
    fleet
    0.16
    ertz
    0.16
    enny
    0.15
     Rem
    0.14
     Tommy
    0.14
    667
    0.14
    iative
    0.14
    981
    0.14
    _binding
    0.14
    Activations Density 0.002%

    No Known Activations