© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 26-LLAMASCOPE-RES-32K
    11. 10809
    Prev
    Next
    INDEX
    Explanations

    phrases related to military services and support for military personnel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CFO
    -0.14
     Lyft
    -0.14
    AZE
    -0.13
     Detective
    -0.13
     Champions
    -0.13
    ÙĦÙĬÙĩ
    -0.13
    HT
    -0.13
     Mansion
    -0.13
     Dynasty
    -0.12
     Champion
    -0.12
    POSITIVE LOGITS
     military
    0.68
     Military
    0.62
     Army
    0.57
    Military
    0.56
     soldiers
    0.55
     soldier
    0.54
     army
    0.52
    è»į
    0.48
    åĨĽ
    0.48
    Army
    0.47
    Activations Density 1.161%

    No Known Activations