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. 17-LLAMASCOPE-RES-32K
    6. 15489
    Prev
    Next
    INDEX
    Explanations

    expressions of estimation, assertion, and belief related to conclusions and findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .pkg
    -0.15
    aked
    -0.14
     measure
    -0.14
     value
    -0.13
     "
    -0.13
    ake
    -0.13
    ultipart
    -0.13
    are
    -0.13
     
    -0.13
    bef
    -0.13
    POSITIVE LOGITS
     rằng
    0.35
     that
    0.34
     bahwa
    0.31
    that
    0.28
     ÏĮÏĦι
    0.26
    	that
    0.26
     dass
    0.24
     ÑĩÑĤо
    0.23
     że
    0.23
     että
    0.22
    Activations Density 0.355%

    No Known Activations