© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-32K
    6. 8885
    Prev
    Next
    INDEX
    Explanations

    key programming and configuration terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ugs
    -0.15
    vil
    -0.15
     Dish
    -0.15
     Há»ĵng
    -0.14
    nga
    -0.14
    ÅĻÃŃm
    -0.14
    emoji
    -0.14
    cai
    -0.14
    igos
    -0.14
    Twig
    -0.14
    POSITIVE LOGITS
    ONEY
    0.15
     gan
    0.15
    ÑĦиÑĨи
    0.15
    iesz
    0.14
    vertise
    0.14
     Bair
    0.14
    å½ĵ
    0.14
    YN
    0.14
    oney
    0.14
    amac
    0.13
    Activations Density 0.000%

    No Known Activations