© 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. 14-LLAMASCOPE-RES-32K
    11. 13186
    Prev
    Next
    INDEX
    Explanations

    aspects related to health and safety measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à¹Īà¸Ńà¸Ļ
    -0.17
     Lion
    -0.16
    OOK
    -0.15
     poh
    -0.15
     wys
    -0.14
    ä½ı
    -0.14
    istrovstvÃŃ
    -0.14
    íį¼
    -0.14
    ãģĤ
    -0.14
    QUIRE
    -0.14
    POSITIVE LOGITS
     Horton
    0.14
    esan
    0.14
    èĦĤ
    0.14
    orrow
    0.14
    ayo
    0.14
    Å¡ÃŃ
    0.13
     messaging
    0.13
    én
    0.13
    ayet
    0.13
    ancel
    0.13
    Activations Density 0.040%

    No Known Activations