© 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. 18589
    Prev
    Next
    INDEX
    Explanations

    instances of social dynamics and personal relationships

    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
     Discipline
    -0.26
    [dir
    -0.22
     Discord
    -0.22
     DataManager
    -0.22
    /div
    -0.21
     Delegate
    -0.21
     Deutsch
    -0.21
     datap
    -0.21
    datatype
    -0.21
     DataType
    -0.20
    POSITIVE LOGITS
    -d
    1.07
    Âłd
    0.86
    -D
    0.82
    _d
    0.75
    ÂłD
    0.71
    "D
    0.63
    _D
    0.61
    	d
    0.59
    D
    0.57
    d
    0.54
    Activations Density 0.840%

    No Known Activations