© 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. 14-LLAMASCOPE-RES-32K
    11. 14713
    Prev
    Next
    INDEX
    Explanations

    phrases related to compliance and regulatory processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -mf
    -0.15
    liž
    -0.15
    oÅĻ
    -0.14
    ÑĢаÑĩ
    -0.14
     Ere
    -0.14
    _PRE
    -0.14
     progress
    -0.14
    udi
    -0.13
    isko
    -0.13
    ÅĻ
    -0.13
    POSITIVE LOGITS
     subsequent
    0.25
     later
    0.24
     ongoing
    0.23
     afterwards
    0.23
    ongo
    0.22
    later
    0.22
     thereafter
    0.20
     post
    0.20
    å¾Įãģ®
    0.20
    ä¹ĭåIJİ
    0.20
    Activations Density 0.333%

    No Known Activations