© 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. 4-LLAMASCOPE-RES-32K
    11. 15129
    Prev
    Next
    INDEX
    Explanations

    phrases that reflect a common or conventional mindset in scientific discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     now
    -0.15
    arger
    -0.15
    midi
    -0.14
    ongo
    -0.14
    alue
    -0.14
    eya
    -0.14
    tas
    -0.14
    CSI
    -0.14
    QUAL
    -0.14
    Dice
    -0.14
    POSITIVE LOGITS
     originally
    0.24
     yesterday
    0.20
     earlier
    0.20
     last
    0.19
     initially
    0.17
     formerly
    0.16
     previously
    0.16
     ì§ĢëĤľ
    0.16
    PELL
    0.15
    æľºåħ³
    0.15
    Activations Density 6.820%

    No Known Activations