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. 8-LLAMASCOPE-RES-32K
    6. 1682
    Prev
    Next
    INDEX
    Explanations

    terms related to brewing processes and project management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÐĴС
    -0.15
    aload
    -0.15
    icode
    -0.15
    @Web
    -0.14
    vsp
    -0.14
    İ
    -0.14
    znik
    -0.14
    инок
    -0.14
    istrovstvÃŃ
    -0.14
    .mount
    -0.14
    POSITIVE LOGITS
     Burl
    0.15
     Marc
    0.15
    wide
    0.15
    isser
    0.15
    ace
    0.15
    standing
    0.14
     Gad
    0.14
    /API
    0.14
    Reporter
    0.14
    ertil
    0.14
    Activations Density 0.271%

    No Known Activations