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. 24-LLAMASCOPE-RES-32K
    6. 5826
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to celebrations and commemorative events, particularly those associated with LGBTQ+ Pride

    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
    окон
    -0.15
    adero
    -0.15
    .codes
    -0.15
     götür
    -0.14
    andbox
    -0.14
    caf
    -0.14
    ãĥ³ãĥĪ
    -0.13
    inyin
    -0.13
     zá
    -0.13
    327
    -0.12
    POSITIVE LOGITS
     celebration
    0.67
     celebrations
    0.60
     celebrate
    0.59
    cele
    0.59
     celebr
    0.58
     Celebr
    0.57
     celebrating
    0.56
    åºĨ
    0.54
     Celebration
    0.52
     celebrates
    0.51
    Activations Density 0.391%

    No Known Activations