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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 72
    Prev
    Next
    INDEX
    Explanations

    references to military experiences and soldiers' training

    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
     Lyft
    -0.15
     Detective
    -0.14
    à¸Ĭà¸Ļ
    -0.14
    à¹ģà¸Ĥ
    -0.13
     Champions
    -0.13
     zbo
    -0.13
    èŃ¦å¯Ł
    -0.13
    erti
    -0.13
     Responsive
    -0.13
    ardin
    -0.12
    POSITIVE LOGITS
     soldier
    0.44
     soldiers
    0.44
    sold
    0.39
     Army
    0.37
    Sold
    0.37
     military
    0.37
     Soldiers
    0.36
     Soldier
    0.35
     Military
    0.34
     army
    0.33
    Activations Density 0.869%

    No Known Activations