© 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. 24393
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Stonewall" in various contexts, particularly relating to LGBTQ+ history and the Stonewall riots

    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
    loid
    -0.15
    aux
    -0.15
    ukan
    -0.15
    zan
    -0.15
    ÑĩÑĥ
    -0.15
    CR
    -0.14
     Williamson
    -0.14
    onde
    -0.14
    ÑģÑĤа
    -0.14
    imized
    -0.14
    POSITIVE LOGITS
    eware
    0.16
    warts
    0.16
    edef
    0.16
    essel
    0.15
     Äijá»ĭnh
    0.15
    eliness
    0.15
    561
    0.15
    GRES
    0.15
    ultan
    0.15
    ợ
    0.15
    Activations Density 0.013%

    No Known Activations