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. 28-LLAMASCOPE-RES-32K
    6. 524
    Prev
    Next
    INDEX
    Explanations

    key metrics and funding-related phrases in educational and research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iens
    -0.17
    rieg
    -0.14
    ваÑĢ
    -0.13
    lle
    -0.13
    eland
    -0.13
    ORG
    -0.13
    aron
    -0.13
    quette
    -0.12
    GES
    -0.12
    اة
    -0.12
    POSITIVE LOGITS
     initiative
    0.52
    init
    0.40
     effort
    0.39
     project
    0.39
     init
    0.36
     Initiative
    0.36
     inici
    0.33
     pilot
    0.33
     initiatives
    0.30
    project
    0.29
    Activations Density 0.300%

    No Known Activations