© 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. 29-LLAMASCOPE-RES-32K
    11. 3669
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals and organizations, particularly related to web content and digital services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PHPExcel
    -0.14
    ãĥĸãĥ«
    -0.14
    /gtest
    -0.13
    ноÑģÑĤ
    -0.13
    ylko
    -0.13
    orough
    -0.13
    adata
    -0.13
    /workspace
    -0.13
    ãģ¡ãĤĩ
    -0.13
    Ñĥг
    -0.12
    POSITIVE LOGITS
     web
    1.36
     Web
    1.36
    Web
    1.30
    web
    1.29
    -web
    1.20
     WEB
    1.16
    _web
    1.13
     Webb
    1.09
    WEB
    1.08
    .web
    1.02
    Activations Density 0.290%

    No Known Activations