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. 2-LLAMASCOPE-RES-32K
    6. 16037
    Prev
    Next
    INDEX
    Explanations

    articles and determiners indicating quantities or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .getElements
    -0.15
    šlo
    -0.15
    ãģ£ãģı
    -0.15
    adlo
    -0.14
    ฯ
    -0.14
    LIKELY
    -0.14
    enda
    -0.14
    оваÑĢи
    -0.14
    ernel
    -0.14
    mage
    -0.14
    POSITIVE LOGITS
     Rule
    0.16
    áº
    0.15
     Industrial
    0.15
    amation
    0.15
     Goth
    0.15
     fest
    0.14
    okin
    0.14
     Fay
    0.14
    鼷
    0.14
     Reader
    0.13
    Activations Density 0.438%

    No Known Activations