© 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. 30-LLAMASCOPE-RES-32K
    11. 9888
    Prev
    Next
    INDEX
    Explanations

    technical terms and structures related to filtering mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONTAL
    -0.18
     Erick
    -0.15
    edin
    -0.14
    èĪĮ
    -0.12
    astle
    -0.12
     stripslashes
    -0.12
    olan
    -0.12
    à¥įध
    -0.12
     Escorts
    -0.12
    کرÛĮ
    -0.12
    POSITIVE LOGITS
     element
    1.23
     Element
    1.06
     elements
    1.04
    element
    1.00
    -element
    0.98
    Element
    0.96
    _element
    0.93
     ELEMENT
    0.93
    åħĥç´ł
    0.91
     Elements
    0.91
    Activations Density 0.353%

    No Known Activations