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. 12-LLAMASCOPE-RES-32K
    6. 28645
    Prev
    Next
    INDEX
    Explanations

    specific terms related to planning and development 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 @ 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
     «
    -0.19
     ``
    -0.17
     "_
    -0.15
    awan
    -0.15
    ãĢģãĢĮ
    -0.14
    ’↵
    -0.14
    ãĢĤãĢĮ
    -0.14
     ãĢĮ
    -0.14
    ãĢĮãģĤ
    -0.14
     _
    -0.14
    POSITIVE LOGITS
    }
    0.19
    ãĢĭçļĦ
    0.16
    ÑĢеб
    0.16
    [/
    0.16
    ãĢĭ
    0.15
    ”çļĦ
    0.15
    reater
    0.14
    ิà¸Ķà¸ķ
    0.14
    ãĢįãģ¨
    0.14
     {?
    0.14
    Activations Density 0.915%

    No Known Activations