© 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. 8-LLAMASCOPE-RES-32K
    11. 20613
    Prev
    Next
    INDEX
    Explanations

    phrasing relating to methodologies or strategies being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ved
    -0.17
    emain
    -0.16
    #__
    -0.16
    erral
    -0.15
    ม
    -0.15
    vez
    -0.14
    èĭ¦
    -0.14
    ogui
    -0.14
    actionDate
    -0.14
    ãĥĥãĤ¯ãĤ¹
    -0.14
    POSITIVE LOGITS
    able
    0.17
    ise
    0.17
     approach
    0.17
    side
    0.16
    remium
    0.15
    ively
    0.15
    weise
    0.15
    phalt
    0.14
     Approach
    0.14
    ERS
    0.13
    Activations Density 0.037%

    No Known Activations