© 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. 29-LLAMASCOPE-RES-32K
    11. 4879
    Prev
    Next
    INDEX
    Explanations

    concepts related to community support and collective well-being

    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
    że
    -0.14
    AZE
    -0.14
    Intensity
    -0.14
    edido
    -0.14
    DataService
    -0.13
     Complexity
    -0.13
    èĥ¸
    -0.13
    UIL
    -0.13
    боÑĢ
    -0.13
    åĬŁ
    -0.13
    POSITIVE LOGITS
     welfare
    0.57
     well
    0.57
     wellbeing
    0.52
    well
    0.48
     Welfare
    0.40
     health
    0.39
     Well
    0.38
     WELL
    0.38
     safety
    0.37
     bien
    0.37
    Activations Density 0.345%

    No Known Activations