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

    Neuronpedia

    Jacobian LensNEW
    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. 25-LLAMASCOPE-RES-32K
    11. 13134
    Prev
    Next
    INDEX
    Explanations

    concepts related to workplace dynamics and employee wellbeing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngo
    -0.14
    afone
    -0.14
    armor
    -0.14
    uil
    -0.13
    ugen
    -0.13
    byn
    -0.13
     Fragen
    -0.13
    ÃŃd
    -0.13
    icens
    -0.13
    é«ĺä¸Ń
    -0.13
    POSITIVE LOGITS
     studies
    0.77
     research
    0.71
     Studies
    0.63
    Studies
    0.60
    research
    0.58
     Research
    0.54
    çłĶ究
    0.52
    Research
    0.52
     study
    0.50
    study
    0.42
    Activations Density 0.488%

    No Known Activations