© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 8-LLAMASCOPE-RES-32K
    11. 6103
    Prev
    Next
    INDEX
    Explanations

    terms related to safety, particularly in the context of accidents and regulations

    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
    iros
    -0.16
    égor
    -0.16
    GPC
    -0.15
    Ïĥμ
    -0.15
    stants
    -0.15
    ãĥ³ãĤ¿
    -0.14
    é¥
    -0.14
    adata
    -0.14
    ãĤ¹ãģ®
    -0.14
    okoj
    -0.14
    POSITIVE LOGITS
     safety
    0.22
     Safety
    0.19
    Safety
    0.18
    afety
    0.17
     hazard
    0.15
     Excell
    0.15
     risk
    0.15
     unsafe
    0.14
     rule
    0.14
    481
    0.14
    Activations Density 0.306%

    No Known Activations