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. 21056
    Prev
    Next
    INDEX
    Explanations

    elements related to rural or agricultural life

    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
     Fauc
    -0.15
    folios
    -0.15
    fish
    -0.14
    èīĩ
    -0.14
     fish
    -0.14
     rừng
    -0.14
    igu
    -0.14
     å¯
    -0.13
     muscle
    -0.13
    uran
    -0.13
    POSITIVE LOGITS
     thresh
    0.38
     harvest
    0.35
     Harvest
    0.33
     harvesting
    0.31
     harvested
    0.31
     hay
    0.29
    thresh
    0.28
     straw
    0.28
    har
    0.26
     sil
    0.25
    Activations Density 0.084%

    No Known Activations