© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 24671
    Prev
    Next
    INDEX
    Explanations

    terms related to financial regulations and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rapper
    -0.18
    legen
    -0.14
     หม
    -0.14
    683
    -0.14
    _ib
    -0.14
     Callable
    -0.14
    veloper
    -0.14
    elin
    -0.14
    callable
    -0.13
    à¥Ĥà¤ļ
    -0.13
    POSITIVE LOGITS
     Dear
    0.29
     DA
    0.29
    Dear
    0.23
     wage
    0.22
     pension
    0.21
     Wage
    0.21
    DA
    0.21
     Employees
    0.21
     employees
    0.21
     Pension
    0.20
    Activations Density 0.013%

    No Known Activations