Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 8-LLAMASCOPE-RES-32K
    6. 4770
    Prev
    Next
    INDEX
    Explanations

    technical programming terms and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cott
    -0.17
    ermo
    -0.16
    vier
    -0.15
    gow
    -0.15
     Bast
    -0.15
    uck
    -0.15
     forth
    -0.14
    ÃŃstica
    -0.14
     Burns
    -0.14
    arga
    -0.13
    POSITIVE LOGITS
    å¹¹ç·ļ
    0.17
    oice
    0.15
    BuilderInterface
    0.15
    çĺ
    0.15
    _ASSUME
    0.15
    DataTask
    0.15
    ä¼ı
    0.14
    iquer
    0.14
    ','','
    0.14
    ATAB
    0.14
    Activations Density 0.175%

    No Known Activations