© 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. 20-LLAMASCOPE-RES-32K
    11. 29487
    Prev
    Next
    INDEX
    Explanations

    phrases related to diversity and inclusivity in support systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ¨ãĤĤ
    -0.15
    uch
    -0.15
    UCH
    -0.14
    arg
    -0.13
    éri
    -0.13
    uja
    -0.13
    unch
    -0.13
    iero
    -0.13
     elsewhere
    -0.13
    rew
    -0.13
    POSITIVE LOGITS
     diversity
    0.72
     variety
    0.69
     diverse
    0.63
     varied
    0.59
     Variety
    0.57
     Diversity
    0.56
     divers
    0.55
     ëĭ¤ìĸij
    0.52
     variation
    0.49
     diversified
    0.47
    Activations Density 0.689%

    No Known Activations