© 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. 24-LLAMASCOPE-RES-32K
    11. 6097
    Prev
    Next
    INDEX
    Explanations

    key corporate acquisitions and mergers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     пÑĢоб
    -0.17
     Futures
    -0.16
    _exports
    -0.15
     smugg
    -0.15
    kses
    -0.14
    aldo
    -0.14
    arkin
    -0.14
    aghan
    -0.14
    rogram
    -0.14
     runApp
    -0.14
    POSITIVE LOGITS
     acquisition
    0.63
     acquisitions
    0.57
     Acquisition
    0.54
     acquired
    0.52
     acquire
    0.50
     acquiring
    0.48
     merger
    0.45
     merg
    0.39
     merge
    0.35
     purchase
    0.34
    Activations Density 0.228%

    No Known Activations