Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 11-LLAMASCOPE-RES-32K
    6. 7299
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety and security measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    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
    -0.16
    IXEL
    -0.15
    å¹¹
    -0.15
    itung
    -0.15
    riba
    -0.15
     Wenger
    -0.15
    yas
    -0.15
     nouve
    -0.15
    upal
    -0.14
    allas
    -0.14
    POSITIVE LOGITS
     safety
    0.33
     Safety
    0.25
     security
    0.24
     protection
    0.24
    å®īåħ¨
    0.22
    /security
    0.22
    afety
    0.22
    Safety
    0.20
    à¸Ľà¸¥à¸Ńà¸Ķà¸ł
    0.19
    -security
    0.19
    Activations Density 0.559%

    No Known Activations