Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2590
    Prev
    Next
    INDEX
    Explanations

    activities and events related to attending social gatherings and games

    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
    á»įc
    -0.16
    istring
    -0.15
    udas
    -0.15
    uge
    -0.15
    -toggler
    -0.14
    odem
    -0.14
    apur
    -0.14
    ams
    -0.14
    ust
    -0.14
     trá»Ŀi
    -0.14
    POSITIVE LOGITS
     events
    0.19
     lectures
    0.17
     preview
    0.16
     imperson
    0.16
     races
    0.15
     movies
    0.15
     event
    0.15
     previews
    0.15
     secular
    0.14
    /watch
    0.14
    Activations Density 0.123%

    No Known Activations