© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 30845
    Prev
    Next
    INDEX
    Explanations

    elements related to Indian culture and society, particularly in the context of family and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Appalachian
    -0.14
     Wyoming
    -0.14
    à¥Ĥà¤ģ
    -0.14
     Knoxville
    -0.13
     Tennessee
    -0.13
     Tacoma
    -0.13
     Oregon
    -0.13
    à¥ģà¤ģ
    -0.13
     Spokane
    -0.13
     Latino
    -0.13
    POSITIVE LOGITS
     India
    0.48
     Bhar
    0.47
     Delhi
    0.46
     Maharashtra
    0.46
     Gujarat
    0.45
     Mumbai
    0.45
     Indian
    0.45
    India
    0.44
     Karnataka
    0.44
     Hindi
    0.43
    Activations Density 7.985%

    No Known Activations