© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-32K
    11. 889
    Prev
    Next
    INDEX
    Explanations

    technical terms associated with image processing and digital signal processing that involve calculations and parameters for rendering images

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _projects
    -0.16
    wik
    -0.15
    Projects
    -0.15
     ë¡
    -0.15
     Projects
    -0.14
    _dicts
    -0.14
    NAMESPACE
    -0.14
    ilos
    -0.14
    Maps
    -0.14
    οÏĤ
    -0.14
    POSITIVE LOGITS
     individual
    0.30
     elements
    0.29
     cells
    0.27
    individual
    0.25
     pixels
    0.25
     Individual
    0.24
     components
    0.23
    .elements
    0.23
     atoms
    0.22
     ingredients
    0.22
    Activations Density 0.597%

    No Known Activations