© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 31-LLAMASCOPE-RES-32K
    11. 16474
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to medical and ethical discussions surrounding hospital practices and responsibilities

    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
     delivering
    -0.31
     acquiring
    -0.31
     transferring
    -0.31
     exchanging
    -0.31
     catching
    -0.30
     releasing
    -0.30
     storing
    -0.30
     capturing
    -0.30
     pushing
    -0.30
     seizing
    -0.30
    POSITIVE LOGITS
    éļª
    0.10
    ãĢģãĤĦ
    0.10
     пÑĢоÑĦеÑģÑģионалÑĮ
    0.10
    âĦĸâĦĸ
    0.10
    ãĢĤéĤ£
    0.10
    волÑı
    0.09
    надлеж
    0.09
    ãģĹãĤĩ
    0.09
    åĭĻ
    0.09
    ãģªãģijãĤĮãģ°
    0.08
    Activations Density 4.501%

    No Known Activations