© 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. 30-LLAMASCOPE-RES-32K
    11. 10796
    Prev
    Next
    INDEX
    Explanations

    phrases related to help, assistance, and support, particularly in the context of personal and professional growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trand
    -0.15
     YÃĸ
    -0.14
    Harness
    -0.14
    Æ°a
    -0.14
    åł
    -0.13
    .forRoot
    -0.13
    าหล
    -0.12
    iveau
    -0.12
     ActionTypes
    -0.12
    ừa
    -0.12
    POSITIVE LOGITS
     help
    1.00
    help
    0.86
     Help
    0.82
    -help
    0.81
    Help
    0.77
     helps
    0.76
     HELP
    0.75
    帮åĬ©
    0.74
     assistance
    0.74
     assist
    0.73
    Activations Density 0.505%

    No Known Activations