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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 24-LLAMASCOPE-RES-32K
    6. 21033
    Prev
    Next
    INDEX
    Explanations

    expressions related to seasonal changes and feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Easter
    -0.35
     Valentine
    -0.35
    February
    -0.34
    January
    -0.33
     Christmas
    -0.33
    Feb
    -0.32
     æĺ¥
    -0.32
    æĺ¥
    -0.32
    Christmas
    -0.31
     jan
    -0.30
    POSITIVE LOGITS
     Sept
    0.84
    Sept
    0.75
     September
    0.74
    September
    0.71
     sept
    0.71
     Sep
    0.71
    Sep
    0.66
     Oct
    0.65
     SEP
    0.62
     september
    0.62
    Activations Density 0.408%

    No Known Activations