© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 22272
    Prev
    Next
    INDEX
    Explanations

    regulatory and oversight-related terms in the context of gaming and advertising

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nex
    -0.19
    วà¸Ļ
    -0.15
    arty
    -0.14
    à¸Ĺà¸Ńà¸ĩ
    -0.14
    ivas
    -0.14
    nee
    -0.14
    argout
    -0.13
    rin
    -0.13
    aoke
    -0.13
    annel
    -0.13
    POSITIVE LOGITS
     regulator
    0.37
     regulators
    0.35
     authorities
    0.30
     regulatory
    0.28
     watchdog
    0.27
     Authority
    0.27
     Competition
    0.26
     authority
    0.25
     Securities
    0.24
     Authorities
    0.23
    Activations Density 0.148%

    No Known Activations