© 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. 31-LLAMASCOPE-RES-32K
    11. 19124
    Prev
    Next
    INDEX
    Explanations

    phrases related to danger and protection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .habbo
    -0.14
    .componentInstance
    -0.12
    å¡ij
    -0.12
    ä¸ĬãģĮ
    -0.12
    HORT
    -0.12
    $sub
    -0.12
     bụ
    -0.12
    .Dispatcher
    -0.12
     оÑĤказ
    -0.11
    è¨ĵ
    -0.11
    POSITIVE LOGITS
     danger
    0.36
     view
    0.34
     reach
    0.33
     harm
    0.32
     range
    0.29
     sight
    0.29
     harms
    0.29
     direct
    0.26
     dangers
    0.26
     potential
    0.25
    Activations Density 0.230%

    No Known Activations