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. 12-LLAMASCOPE-RES-32K
    6. 26343
    Prev
    Next
    INDEX
    Explanations

    terms and settings related to system administration and configuration in software

    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
    uja
    -0.15
    eken
    -0.15
     Branch
    -0.15
    æī§
    -0.15
    Branch
    -0.15
    igious
    -0.14
    æ´²
    -0.14
    eyse
    -0.14
    ÙĪØ²ÛĮ
    -0.14
    eyin
    -0.14
    POSITIVE LOGITS
     onHide
    0.15
     Addison
    0.15
    463
    0.15
    .githubusercontent
    0.15
    ird
    0.14
     Brit
    0.14
     bulls
    0.14
    ģında
    0.14
    759
    0.13
    unt
    0.13
    Activations Density 0.028%

    No Known Activations