© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 12-LLAMASCOPE-RES-32K
    6. 14298
    Prev
    Next
    INDEX
    Explanations

    specific programming keywords and structures related to code definitions and data models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ymoon
    -0.15
    acci
    -0.15
    Thunk
    -0.14
     sequelize
    -0.14
    urr
    -0.14
    .lazy
    -0.14
    ç½®
    -0.13
    -bin
    -0.13
    andWhere
    -0.13
    kili
    -0.13
    POSITIVE LOGITS
    esser
    0.15
    zia
    0.15
     Dud
    0.15
     Meyer
    0.14
    Optimizer
    0.14
    eyer
    0.14
    bd
    0.14
    εÏģι
    0.14
    .newLine
    0.14
    imoto
    0.14
    Activations Density 0.274%

    No Known Activations