© 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 EvalsExportsinterp-engineNEWAPI 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. 14489
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate significant warnings or consequences, particularly in health and safety contexts

    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
     ,↵
    -0.18
     .↵
    -0.16
    >\↵
    -0.16
     ;č↵
    -0.15
    \↵
    -0.14
    ;\↵
    -0.14
    placeholders
    -0.14
    .*↵
    -0.14
     *,↵
    -0.13
     плÑİ
    -0.13
    POSITIVE LOGITS
    	Read
    0.23
     [âĢ¦]↵↵
    0.23
    0.22
     photo
    0.21
     read
    0.20
     [âĢ¦]
    0.20
     âĢ¦↵↵
    0.20
    0.20
     �
    0.19
     below
    0.19
    Activations Density 1.388%

    No Known Activations