© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 18-LLAMASCOPE-RES-32K
    11. 27156
    Prev
    Next
    INDEX
    Explanations

    expressions related to security and protection measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    анÑĤи
    -0.15
    pyx
    -0.14
    iaux
    -0.14
    γνÏī
    -0.14
    straints
    -0.14
     à¸ģระ
    -0.14
    vez
    -0.14
     forgiving
    -0.13
    Foreground
    -0.13
     Operator
    -0.13
    POSITIVE LOGITS
     protection
    0.60
     Protection
    0.50
     protect
    0.49
     security
    0.47
     protecting
    0.46
     protective
    0.43
    ä¿ĿæĬ¤
    0.42
    Protection
    0.42
    protect
    0.42
     protects
    0.41
    Activations Density 0.263%

    No Known Activations