© 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. 30-LLAMASCOPE-RES-32K
    11. 5750
    Prev
    Next
    INDEX
    Explanations

    numerical expressions or references to dates and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    4
    -0.50
     fourth
    -0.49
     Fourth
    -0.48
     FOUR
    -0.47
     four
    -0.45
    four
    -0.44
    -four
    -0.43
     Four
    -0.43
    åĽĽ
    -0.43
    Fourth
    -0.41
    POSITIVE LOGITS
    urdu
    0.16
    0
    0.15
    Ùł
    0.15
    elper
    0.14
    arding
    0.14
    Īëĭ¤
    0.14
    ०
    0.13
    ï¼IJ
    0.13
    utzer
    0.13
    ại
    0.13
    Activations Density 0.061%

    No Known Activations