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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5722
    Prev
    Next
    INDEX
    Explanations

    content related to travel logistics and transportation options

    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
     Harlem
    -0.19
     Hudson
    -0.18
     Cleveland
    -0.18
     Snyder
    -0.16
     Columbus
    -0.16
     Ohio
    -0.16
    âĦĸâĦĸ
    -0.15
     ohio
    -0.15
     Columbia
    -0.15
    Ohio
    -0.15
    POSITIVE LOGITS
     Thai
    0.68
     Thailand
    0.66
     Bangkok
    0.65
    Thai
    0.63
     thai
    0.49
     THB
    0.43
     Thái
    0.42
     ฿
    0.42
     Tham
    0.41
     Patt
    0.39
    Activations Density 0.094%

    No Known Activations