© 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. 11-LLAMASCOPE-RES-32K
    11. 7030
    Prev
    Next
    INDEX
    Explanations

    references to narratives, projects, and organized activities, especially in a collective or procedural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unta
    -0.15
    ibar
    -0.15
    æ½
    -0.14
     Luc
    -0.14
    lyn
    -0.14
    缩
    -0.14
    olla
    -0.13
    733
    -0.13
     vir
    -0.13
     Tunnel
    -0.13
    POSITIVE LOGITS
    ariat
    0.17
    jos
    0.15
    iones
    0.15
    室
    0.15
     tslint
    0.14
     MetroFramework
    0.14
    pedia
    0.14
    æĸĩçĮ®
    0.14
    _AMD
    0.14
    ammer
    0.13
    Activations Density 0.021%

    No Known Activations