© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 24-LLAMASCOPE-RES-32K
    11. 6807
    Prev
    Next
    INDEX
    Explanations

    phrases related to competitive sports dynamics, particularly in cycling

    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
    ç²Ĺ
    -0.17
    /lists
    -0.14
    rett
    -0.14
     campaigns
    -0.14
    ÏĢλ
    -0.14
    rian
    -0.13
    quate
    -0.13
     bouncing
    -0.13
     bounce
    -0.13
    ãģĿ
    -0.13
    POSITIVE LOGITS
     drafting
    0.18
    .AppSettings
    0.17
    Gap
    0.17
    -gap
    0.16
     lap
    0.16
    printer
    0.16
     Gap
    0.16
    Printer
    0.16
     grup
    0.16
     conserv
    0.16
    Activations Density 0.123%

    No Known Activations