© 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. 20-LLAMASCOPE-RES-32K
    11. 12870
    Prev
    Next
    INDEX
    Explanations

    phrases related to health impacts and medical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arden
    -0.14
    emark
    -0.13
    ÏĥÏĦε
    -0.13
    ÏĢλα
    -0.13
     lagi
    -0.13
     cripp
    -0.13
    -held
    -0.13
     crushers
    -0.13
    isset
    -0.13
    hangi
    -0.13
    POSITIVE LOGITS
     due
    0.39
    due
    0.35
     caused
    0.34
     Due
    0.30
    _due
    0.29
    Due
    0.28
     CAUSED
    0.28
    à¸Īาà¸ģà¸ģาร
    0.26
     from
    0.25
    çĶ±äºİ
    0.24
    Activations Density 0.330%

    No Known Activations