© 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. 31-LLAMASCOPE-RES-32K
    11. 18494
    Prev
    Next
    INDEX
    Explanations

    mentions of sports and entertainment venues and their activities

    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
     ngang
    -0.15
     кваÑĢÑĤи
    -0.15
    ẻ
    -0.15
    รà¸ĵ
    -0.14
    /////////////////////////////////////////////////////////////////////////////↵
    -0.13
    .easing
    -0.13
    _FIFO
    -0.13
    //{{
    -0.13
    ouro
    -0.13
    ldr
    -0.13
    POSITIVE LOGITS
     Arena
    0.54
     arena
    0.51
    arena
    0.44
    Arena
    0.43
     Stadium
    0.41
     stadium
    0.41
     arenas
    0.41
     Auditor
    0.39
     auditor
    0.37
     Amph
    0.36
    Activations Density 0.127%

    No Known Activations