© 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. 18-LLAMASCOPE-RES-32K
    11. 17024
    Prev
    Next
    INDEX
    Explanations

    mentions of women with the title "Ms" followed by their last names or initials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -0.15
    him
    -0.15
    his
    -0.15
     mmc
    -0.15
    ha
    -0.14
    à¸Ĺาà¸ĩ
    -0.14
     Microwave
    -0.14
    lint
    -0.14
    cio
    -0.14
    sted
    -0.14
    POSITIVE LOGITS
     herself
    0.18
    ãĢħ
    0.15
    /man
    0.15
     ấy
    0.15
    ujet
    0.15
    她们
    0.14
     Rowling
    0.14
    ouri
    0.14
     Cle
    0.13
    UFFER
    0.13
    Activations Density 0.024%

    No Known Activations