© 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. 20-LLAMASCOPE-RES-32K
    6. 27050
    Prev
    Next
    INDEX
    Explanations

    discussions related to educational standards and guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ļĮ
    -0.14
    baar
    -0.14
     brighter
    -0.13
    om
    -0.13
     redeemed
    -0.13
    Redis
    -0.13
    ##_
    -0.13
    ya
    -0.13
     ex
    -0.13
     Thesis
    -0.13
    POSITIVE LOGITS
     update
    0.20
     updating
    0.19
     edition
    0.19
     draft
    0.18
    unge
    0.18
     Edition
    0.18
     sát
    0.18
     drafts
    0.18
    imals
    0.17
    panion
    0.17
    Activations Density 0.109%

    No Known Activations