© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 19211
    Prev
    Next
    INDEX
    Explanations

    phrases and references related to infrastructure and community support initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Firstly
    -0.13
     nackte
    -0.12
     eoq
    -0.12
    ãģ£ãģį
    -0.12
    нок
    -0.12
     jinak
    -0.11
    ÄŁinden
    -0.11
     Mostly
    -0.11
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.11
    Memcpy
    -0.11
    POSITIVE LOGITS
     subsequent
    0.64
     accompanying
    0.61
     related
    0.60
     associated
    0.58
     other
    0.57
     corresponding
    0.52
     adjacent
    0.51
     adjoining
    0.50
     ensuing
    0.49
     companion
    0.48
    Activations Density 1.161%

    No Known Activations