© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 27-LLAMASCOPE-RES-32K
    6. 678
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding definitions and their implications related to various topics such as morality, poverty, and art

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Deng
    -0.13
    ading
    -0.13
    λÏİ
    -0.13
    ichtet
    -0.12
    -toggler
    -0.12
    =YES
    -0.12
    utting
    -0.12
    GenerationStrategy
    -0.12
    lingen
    -0.12
     culmination
    -0.12
    POSITIVE LOGITS
     definition
    1.25
     definitions
    1.09
     Definition
    1.05
    definition
    1.04
    -definition
    0.97
    Definition
    0.96
     Definitions
    0.90
    å®ļä¹ī
    0.88
    definitions
    0.88
     defined
    0.88
    Activations Density 0.374%

    No Known Activations