Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 28-LLAMASCOPE-RES-32K
    6. 452
    Prev
    Next
    INDEX
    Explanations

    terms related to civilian casualties and the implications of warfare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Expressions
    -0.16
    Å¡tÄĽ
    -0.16
    ibil
    -0.15
     Riot
    -0.15
     Bullet
    -0.15
    ιÏĩ
    -0.15
    å¼ĥ
    -0.14
     mand
    -0.14
    Href
    -0.14
    à¤ľà¤°
    -0.14
    POSITIVE LOGITS
     strikes
    0.44
     strike
    0.39
     Strikes
    0.36
     Strike
    0.33
     airstrikes
    0.31
     airst
    0.31
    Strike
    0.29
     bombing
    0.29
    strike
    0.29
    _strike
    0.28
    Activations Density 0.066%

    No Known Activations