Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 18176
    Prev
    Next
    INDEX
    Explanations

    references to time, particularly focusing on the afternoon and scheduling activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nights
    -0.21
     Sleep
    -0.19
     Mondays
    -0.17
     Dawn
    -0.16
    anko
    -0.15
    edir
    -0.15
    months
    -0.15
    Sleep
    -0.15
     sleep
    -0.15
     midnight
    -0.15
    POSITIVE LOGITS
     afternoon
    0.88
     evening
    0.51
     tarde
    0.49
    -after
    0.46
     late
    0.45
     lunch
    0.43
     PM
    0.41
    åįĪ
    0.40
     ìĺ¤íĽĦ
    0.39
     After
    0.39
    Activations Density 0.225%

    No Known Activations