© 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. 15448
    Prev
    Next
    INDEX
    Explanations

    references to protective gear and safety equipment, particularly gloves

    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
     hips
    -0.18
     legs
    -0.17
    stalk
    -0.17
    ihan
    -0.16
    -legged
    -0.16
    obo
    -0.15
     Legs
    -0.15
     thigh
    -0.15
     blanket
    -0.15
    onical
    -0.14
    POSITIVE LOGITS
     gloves
    0.45
     glove
    0.45
     Gloves
    0.44
     palm
    0.35
     Glo
    0.35
     fingers
    0.35
     finger
    0.31
     Palm
    0.31
     glo
    0.31
     Finger
    0.31
    Activations Density 0.054%

    No Known Activations