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. 23-LLAMASCOPE-RES-32K
    6. 28324
    Prev
    Next
    INDEX
    Explanations

    culinary terms and descriptions related to food and dining experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orate
    -0.15
     Sunder
    -0.15
    ipse
    -0.14
     Krish
    -0.14
    Rated
    -0.14
     chocol
    -0.14
    è¸ı
    -0.14
    Ấ
    -0.13
    _userdata
    -0.13
    istrovstvÃŃ
    -0.13
    POSITIVE LOGITS
     menu
    0.25
     specials
    0.23
     served
    0.22
     options
    0.21
     rotate
    0.20
    menu
    0.19
    options
    0.19
     option
    0.19
    OPTIONS
    0.18
    order
    0.18
    Activations Density 0.083%

    No Known Activations