© 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. 25-LLAMASCOPE-RES-32K
    11. 22397
    Prev
    Next
    INDEX
    Explanations

    references to military actions and international conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à¸ķ
    -0.15
     sublic
    -0.15
    sett
    -0.15
    289
    -0.15
    isen
    -0.15
     Mao
    -0.14
    auty
    -0.14
     amnesty
    -0.14
     pale
    -0.14
    anka
    -0.14
    POSITIVE LOGITS
     Sole
    0.27
     Iranians
    0.25
     Iranian
    0.25
     Horm
    0.24
     Strait
    0.24
     Tehran
    0.22
     Iran
    0.20
     Revolutionary
    0.19
     IR
    0.18
     Pompeo
    0.18
    Activations Density 0.049%

    No Known Activations