© 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. 21242
    Prev
    Next
    INDEX
    Explanations

    significant words or phrases indicating key concepts or elements in a discussion

    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
    .ua
    -0.14
    Towards
    -0.14
    äºĪ
    -0.13
    pectrum
    -0.13
    orra
    -0.13
    оÑĤе
    -0.13
    oogle
    -0.13
    ¢åįķ
    -0.13
     surrounding
    -0.12
    Ïģί
    -0.12
    POSITIVE LOGITS
     things
    0.20
     reason
    0.19
     tasks
    0.19
     reasons
    0.17
     ways
    0.16
     main
    0.16
    tasks
    0.16
     thing
    0.15
     fun
    0.15
     major
    0.15
    Activations Density 0.033%

    No Known Activations