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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1016
    Prev
    Next
    INDEX
    Explanations

    elements related to image metadata and descriptions

    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
     images
    -0.21
     logo
    -0.18
    images
    -0.18
     pictures
    -0.18
     photographs
    -0.18
     Bilder
    -0.18
     Images
    -0.18
    -images
    -0.17
     imagery
    -0.17
     Logo
    -0.17
    POSITIVE LOGITS
     crops
    0.21
     caption
    0.21
     Caption
    0.20
     crop
    0.19
    crop
    0.18
     quality
    0.18
    _caption
    0.18
     captions
    0.18
     Quality
    0.18
    caption
    0.18
    Activations Density 0.053%

    No Known Activations