© 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. 15-LLAMASCOPE-RES-32K
    11. 15614
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety and handling procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     capital
    -0.15
    ücü
    -0.14
    uggage
    -0.14
    icket
    -0.14
    iral
    -0.14
    ạng
    -0.13
     Williamson
    -0.13
    igon
    -0.13
    à¸Īร
    -0.13
    undra
    -0.13
    POSITIVE LOGITS
     saf
    0.21
     safely
    0.21
     unsafe
    0.21
     hazardous
    0.21
    afe
    0.20
    -safe
    0.20
     safest
    0.20
     dangerous
    0.20
     safety
    0.20
     danger
    0.19
    Activations Density 0.205%

    No Known Activations