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. 13-LLAMASCOPE-RES-32K
    6. 630
    Prev
    Next
    INDEX
    Explanations

    references to external websites and their privacy policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ake
    -0.18
    amer
    -0.17
    emi
    -0.15
     ang
    -0.15
    omer
    -0.15
    akes
    -0.15
    UIS
    -0.15
     Hass
    -0.14
    ApiClient
    -0.14
    оÑĤи
    -0.14
    POSITIVE LOGITS
    tuk
    0.15
    taÅŁ
    0.15
    é¼
    0.15
    оÑĢаÑı
    0.15
     autre
    0.15
    -counter
    0.15
     altre
    0.14
    CEPTION
    0.14
    -thumbnails
    0.14
    mlink
    0.14
    Activations Density 0.017%

    No Known Activations