© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 20-LLAMASCOPE-RES-32K
    11. 28761
    Prev
    Next
    INDEX
    Explanations

    phrases related to contrasting viewpoints and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģªãģĮãĤī
    -0.16
    )prepare
    -0.14
     ?>/
    -0.14
    елем
    -0.13
    treeview
    -0.13
     kurulan
    -0.13
     kullanılan
    -0.13
    adder
    -0.13
    ÑĢоÑĪ
    -0.13
     Sort
    -0.12
    POSITIVE LOGITS
     which
    0.99
    which
    0.84
     Which
    0.78
     WHICH
    0.73
    Which
    0.72
     wich
    0.57
    .which
    0.56
     οÏĢοία
    0.50
     οÏĢοίο
    0.49
     cuales
    0.49
    Activations Density 0.692%

    No Known Activations