© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 22265
    Prev
    Next
    INDEX
    Explanations

    myths and facts related to COVID-19

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inform
    -0.16
    elson
    -0.14
     è¨Ģ
    -0.14
    (æĹ¥
    -0.14
    stÅĻÃŃ
    -0.13
    VOKE
    -0.13
    åĬ¡
    -0.13
    Pooling
    -0.13
    /vnd
    -0.13
    TEGER
    -0.13
    POSITIVE LOGITS
     travellers
    0.15
     decl
    0.15
     website
    0.15
    529
    0.14
    ILD
    0.14
    é¢Ĩ导
    0.14
    estate
    0.14
     resolutions
    0.14
     seo
    0.14
     dental
    0.14
    Activations Density 0.403%

    No Known Activations