© 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. 16-LLAMASCOPE-RES-32K
    11. 6705
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to leadership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neys
    -0.18
    337
    -0.17
    ori
    -0.17
     pie
    -0.17
    pie
    -0.17
     Pie
    -0.16
    -Sah
    -0.16
    imeo
    -0.15
    ulo
    -0.15
    enga
    -0.15
    POSITIVE LOGITS
    -edge
    0.28
     edge
    0.21
    leading
    0.19
    lights
    0.18
    gers
    0.17
    haft
    0.17
    edge
    0.16
    辺
    0.16
    roit
    0.16
    ROTO
    0.15
    Activations Density 0.062%

    No Known Activations