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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-LLAMASCOPE-RES-32K
    6. 3807
    Prev
    Next
    INDEX
    Explanations

    titles and roles related to coordinators and managers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amed
    -0.15
    ALLE
    -0.15
    urge
    -0.15
    onya
    -0.15
    ç§»åΰ
    -0.15
    481
    -0.14
    ucci
    -0.14
    elp
    -0.14
    asser
    -0.14
    aq
    -0.14
    POSITIVE LOGITS
     Burton
    0.17
     nad
    0.16
    resultSet
    0.15
    ãĥ«ãĥī
    0.15
    à¥įशन
    0.15
    arters
    0.15
    ilter
    0.14
    swagen
    0.14
    vided
    0.14
     Hib
    0.14
    Activations Density 0.061%

    No Known Activations