© 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. 31-LLAMASCOPE-RES-32K
    11. 20226
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their affiliations or contributions in research or academia

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     köln
    -0.14
    ÐIJÑĢÑħÑĸв
    -0.12
     NASCAR
    -0.12
     Vermont
    -0.12
    รà¸ģ
    -0.12
     Há»ĩ
    -0.12
    lahoma
    -0.12
     knull
    -0.11
    âĦĸâĦĸ
    -0.11
     Ä°talya
    -0.11
    POSITIVE LOGITS
     Chinese
    0.64
     China
    0.60
     Beijing
    0.58
     Guang
    0.57
     Jiang
    0.55
    Chinese
    0.54
     Shanghai
    0.54
     Qing
    0.54
    China
    0.52
     Zhang
    0.52
    Activations Density 2.856%

    No Known Activations