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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 17539
    Prev
    Next
    INDEX
    Explanations

    details related to events and social gatherings, particularly those that occur at night

    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
     Lunch
    -0.25
     breakfast
    -0.23
     noon
    -0.23
     Morning
    -0.22
     Breakfast
    -0.22
     Noon
    -0.22
     lunches
    -0.22
     brunch
    -0.21
     sunlight
    -0.21
     lunch
    -0.20
    POSITIVE LOGITS
     night
    0.84
    night
    0.69
     nights
    0.69
    å¤ľ
    0.66
    -night
    0.66
     Night
    0.65
    Night
    0.63
     NIGHT
    0.63
     tonight
    0.63
    Tonight
    0.61
    Activations Density 0.244%

    No Known Activations