© 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. 24-LLAMASCOPE-RES-32K
    11. 19798
    Prev
    Next
    INDEX
    Explanations

    references to medical emergencies and rescue operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RAIN
    -0.14
    lez
    -0.14
    егÑĢа
    -0.14
    代çIJĨ
    -0.14
    contre
    -0.14
    ewood
    -0.13
    agle
    -0.13
    é»
    -0.13
    ionic
    -0.13
    ngr
    -0.13
    POSITIVE LOGITS
     param
    0.47
     Param
    0.47
     amb
    0.42
     Amb
    0.41
     ambulance
    0.40
    param
    0.39
    Param
    0.38
    -param
    0.37
     PARAM
    0.37
    .param
    0.37
    Activations Density 0.059%

    No Known Activations