© 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. 23-LLAMASCOPE-RES-32K
    11. 1273
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS attributes related to color styling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -black
    -0.23
     black
    -0.22
    /black
    -0.19
    .black
    -0.18
     Black
    -0.18
    black
    -0.18
    :black
    -0.17
     BLACK
    -0.17
     dark
    -0.16
    é»ij
    -0.16
    POSITIVE LOGITS
    eeee
    0.16
    EIF
    0.16
     Whites
    0.16
    ãĥ©ãĤ¤ãĥĪ
    0.16
    enheim
    0.15
    White
    0.15
    εδ
    0.14
    λεÏħ
    0.14
    Signals
    0.14
    odef
    0.14
    Activations Density 0.009%

    No Known Activations