© 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. 13-LLAMASCOPE-RES-32K
    6. 14434
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and constructs, specifically focusing on variable declarations and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mir
    -0.15
     u
    -0.14
     l
    -0.14
     cons
    -0.14
    ird
    -0.14
     leading
    -0.14
     industrial
    -0.14
     w
    -0.14
     n
    -0.14
    -grade
    -0.14
    POSITIVE LOGITS
    readcr
    0.18
    alore
    0.17
    ault
    0.15
    olland
    0.15
    adata
    0.14
    BuilderFactory
    0.14
    ître
    0.14
    .nlm
    0.14
    itur
    0.14
    лик
    0.14
    Activations Density 0.052%

    No Known Activations