© 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. 30-LLAMASCOPE-RES-32K
    11. 6725
    Prev
    Next
    INDEX
    Explanations

    references to security policies and restrictions in code-related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jadx
    -0.15
     cellForRowAtIndexPath
    -0.14
    ÑĢовиÑĩ
    -0.14
    ä¸ĺ
    -0.14
    .mybatisplus
    -0.14
    ideon
    -0.13
    _skin
    -0.13
    TypeId
    -0.13
    .setOutput
    -0.13
     AVL
    -0.13
    POSITIVE LOGITS
     origin
    0.34
     Origin
    0.31
     origins
    0.30
     cross
    0.28
     Cross
    0.28
    Origin
    0.27
     crossorigin
    0.27
    -origin
    0.26
     Same
    0.25
     policy
    0.24
    Activations Density 0.042%

    No Known Activations