© 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. 28-LLAMASCOPE-RES-32K
    11. 28965
    Prev
    Next
    INDEX
    Explanations

    disruptions to established routines and patterns in daily life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    deaux
    -0.18
    á»Ń
    -0.15
    usi
    -0.14
    grade
    -0.14
     æĻ´
    -0.14
    ilon
    -0.14
    Æ°Æ¡i
    -0.14
    ëĿ½
    -0.14
    usz
    -0.13
    enek
    -0.13
    POSITIVE LOGITS
     pattern
    0.50
     patterns
    0.48
     Pattern
    0.46
     Patterns
    0.45
    Pattern
    0.45
    pattern
    0.44
    -pattern
    0.41
    patterns
    0.41
    Patterns
    0.39
    _pattern
    0.37
    Activations Density 0.020%

    No Known Activations