© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 21311
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to numbers and their arrangement or format

    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
     sevent
    -0.19
     Nin
    -0.18
    issance
    -0.17
    entieth
    -0.16
     xxx
    -0.15
    uyên
    -0.15
    ost
    -0.15
     Seven
    -0.14
    yles
    -0.14
     oct
    -0.14
    POSITIVE LOGITS
    12
    0.94
     Twelve
    0.81
     twelve
    0.79
    åįģäºĮ
    0.73
     XII
    0.63
    Û±Û²
    0.59
    Tw
    0.56
     tw
    0.50
     Tw
    0.50
    012
    0.49
    Activations Density 0.249%

    No Known Activations