© 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. 31-LLAMASCOPE-RES-32K
    11. 2359
    Prev
    Next
    INDEX
    Explanations

    references to safety protocols and medical precautions related to COVID-19

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    goo
    -0.20
    	http
    -0.19
     http
    -0.18
    ï¼Īå¹³æĪIJ
    -0.18
    .wik
    -0.18
    :http
    -0.18
    http
    -0.18
    =http
    -0.17
    (http
    -0.17
    .googlecode
    -0.16
    POSITIVE LOGITS
     COVID
    0.84
     Covid
    0.77
     covid
    0.75
    COVID
    0.73
     coronavirus
    0.73
     Coronavirus
    0.71
     pandemic
    0.69
     lockdown
    0.56
     quarantine
    0.52
     ì½Ķë¡ľëĤĺ
    0.52
    Activations Density 1.705%

    No Known Activations