© 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. 13-LLAMASCOPE-RES-32K
    11. 27810
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" in various contexts and its interactions with other words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĹ
    -0.15
     DefaultValue
    -0.14
    lesia
    -0.14
     vak
    -0.14
    reative
    -0.14
    erner
    -0.14
    ĨĴ
    -0.14
    ablo
    -0.14
     Äijâu
    -0.13
    odox
    -0.13
    POSITIVE LOGITS
    /OR
    0.19
    /or
    0.17
     CSL
    0.14
    ÙĦب
    0.14
    IFS
    0.14
    imet
    0.13
     ras
    0.13
    ÑĢал
    0.13
    ylvania
    0.13
     unfolded
    0.13
    Activations Density 0.048%

    No Known Activations