© 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. 22-LLAMASCOPE-RES-32K
    11. 4424
    Prev
    Next
    INDEX
    Explanations

    references to time and duration in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     during
    -0.25
    during
    -0.20
     durante
    -0.19
     During
    -0.18
     throughout
    -0.16
     overnight
    -0.16
     early
    -0.16
     after
    -0.16
     пÑĢоÑĤÑıгом
    -0.15
     late
    -0.15
    POSITIVE LOGITS
     period
    0.20
     periodo
    0.18
    vido
    0.18
     ÙħÛĮÙĦادÛĮ
    0.18
    æľŁ
    0.17
    /post
    0.16
    DataExchange
    0.16
     Ùħباش
    0.15
    PostalCodes
    0.15
    HeaderCode
    0.15
    Activations Density 0.352%

    No Known Activations