© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 29-LLAMASCOPE-RES-32K
    6. 5119
    Prev
    Next
    INDEX
    Explanations

    terminology related to scientific concepts and innovations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estre
    -0.18
     HOLDERS
    -0.14
    alars
    -0.14
     Cold
    -0.14
    heit
    -0.14
     derec
    -0.14
     residency
    -0.13
    preload
    -0.13
    oug
    -0.13
    æĮ¯ãĤĬ
    -0.13
    POSITIVE LOGITS
     solar
    0.31
    Solar
    0.28
     Solar
    0.26
     device
    0.24
     hole
    0.23
     organic
    0.23
     Voc
    0.22
     Hole
    0.22
     devices
    0.22
     Device
    0.22
    Activations Density 0.003%

    No Known Activations