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. 12-LLAMASCOPE-RES-32K
    6. 26363
    Prev
    Next
    INDEX
    Explanations

    references to years, dates, and statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overload
    -0.16
    oge
    -0.16
    mpl
    -0.15
    wo
    -0.14
    inic
    -0.14
    anik
    -0.14
    inia
    -0.14
    /sources
    -0.14
    aise
    -0.13
    ixel
    -0.13
    POSITIVE LOGITS
    ascar
    0.18
    acco
    0.16
     Rou
    0.16
     nieu
    0.14
     casualty
    0.14
     Loft
    0.14
    Ưá»
    0.14
    į¨
    0.14
    _exempt
    0.14
    _feed
    0.13
    Activations Density 0.003%

    No Known Activations