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. 18-LLAMASCOPE-RES-32K
    6. 16514
    Prev
    Next
    INDEX
    Explanations

    references to specific tools and equipment related to gardening and agricultural tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umba
    -0.18
    xn
    -0.14
    riel
    -0.14
    _MACHINE
    -0.13
    thon
    -0.13
    -series
    -0.13
    ÑĥÑĪка
    -0.13
    (())↵
    -0.13
    alley
    -0.13
    itch
    -0.13
    POSITIVE LOGITS
     sorts
    0.17
    zeit
    0.15
     kinds
    0.15
    érc
    0.14
    emos
    0.14
    aseline
    0.14
    è²
    0.13
     zbo
    0.13
    TXT
    0.13
    iar
    0.13
    Activations Density 0.458%

    No Known Activations