© 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. 17-LLAMASCOPE-RES-32K
    11. 26329
    Prev
    Next
    INDEX
    Explanations

    references to time, specifically related to years, months, weeks, and days

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yearly
    -0.20
     annual
    -0.20
     quarterly
    -0.18
     Annual
    -0.18
    weekly
    -0.17
    Weekly
    -0.16
     weekly
    -0.16
    Annual
    -0.16
     annually
    -0.16
    annual
    -0.16
    POSITIVE LOGITS
    occo
    0.18
    /month
    0.16
    ettle
    0.15
    å·¦åı³
    0.15
    ovich
    0.14
     Haz
    0.14
    hythm
    0.14
    aneously
    0.14
    ãģĨãģ¡
    0.14
    tr
    0.14
    Activations Density 0.029%

    No Known Activations