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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 16375
    Prev
    Next
    INDEX
    Explanations

    references to medical treatment and guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     epidemi
    -0.18
     Krank
    -0.18
     lékaÅĻ
    -0.17
    åĮ»åѦ
    -0.17
    çĻĤ
    -0.17
    çĹħ
    -0.16
     بÛĮÙħارÛĮ
    -0.16
    wers
    -0.16
     léka
    -0.15
    æ²»çĸĹ
    -0.15
    POSITIVE LOGITS
     sleep
    0.22
     heart
    0.21
     stroke
    0.21
     screening
    0.20
     screenings
    0.18
     Screening
    0.18
     brain
    0.18
     pain
    0.18
     bone
    0.17
     burn
    0.17
    Activations Density 0.588%

    No Known Activations