© 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. 1835
    Prev
    Next
    INDEX
    Explanations

    data related to medical procedures and health management

    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
     artık
    -0.14
     roÄįnÃŃ
    -0.14
     минÑĥ
    -0.13
    .lazy
    -0.13
    eeper
    -0.13
     ÏĩÏīÏģίÏĤ
    -0.12
    ÑģÑĤÑĢи
    -0.12
     давно
    -0.12
     sözleÅŁ
    -0.12
    åѤ
    -0.12
    POSITIVE LOGITS
     during
    1.10
    during
    0.94
     durante
    0.84
     During
    0.80
    During
    0.75
     während
    0.73
     while
    0.67
     throughout
    0.66
     bÄĽhem
    0.60
     whilst
    0.59
    Activations Density 0.312%

    No Known Activations