© 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. 24-LLAMASCOPE-RES-32K
    11. 6858
    Prev
    Next
    INDEX
    Explanations

    instances of Java data structure creation and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bravo
    -0.16
    uzzi
    -0.15
    _unused
    -0.15
     abre
    -0.15
    -caret
    -0.15
    ubo
    -0.14
    .RegisterType
    -0.14
    aber
    -0.14
    swith
    -0.14
     ach
    -0.14
    POSITIVE LOGITS
     Collections
    0.33
     collections
    0.31
     Collection
    0.30
     collection
    0.30
    Collections
    0.28
     List
    0.28
    Collection
    0.27
     ArrayList
    0.26
    .newArrayList
    0.26
    .Collections
    0.24
    Activations Density 0.044%

    No Known Activations