© 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. 22550
    Prev
    Next
    INDEX
    Explanations

    instances of the word "We" followed by variations of "As" and "In"

    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
    .documentation
    -0.15
    sembly
    -0.15
    ziaÅĤ
    -0.14
    ëŁī
    -0.14
     newX
    -0.14
    ildren
    -0.14
    亮
    -0.13
    COMPARE
    -0.13
    ders
    -0.13
    abouts
    -0.13
    POSITIVE LOGITS
    iland
    0.14
    ÑĤак
    0.13
    opr
    0.13
    andra
    0.13
    entiful
    0.13
    коÑĢиÑģÑĤ
    0.12
    enor
    0.12
    ushman
    0.12
     basename
    0.12
    q
    0.12
    Activations Density 0.157%

    No Known Activations