Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 28-LLAMASCOPE-RES-32K
    6. 29224
    Prev
    Next
    INDEX
    Explanations

    phrases related to coziness and comfort, especially in winter settings

    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
     strap
    -0.15
    ãģ¦ãĤĭ
    -0.15
     Refriger
    -0.15
    é³
    -0.15
     refriger
    -0.15
    禮
    -0.14
    ponsive
    -0.14
    à¥Ĥष
    -0.14
    entr
    -0.13
    liÄį
    -0.13
    POSITIVE LOGITS
     sn
    0.31
     blankets
    0.28
     cozy
    0.27
     blanket
    0.27
     Blank
    0.26
     curl
    0.26
     cose
    0.25
     cosy
    0.25
    blank
    0.24
     coz
    0.24
    Activations Density 0.090%

    No Known Activations