© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 23-LLAMASCOPE-RES-32K
    6. 30406
    Prev
    Next
    INDEX
    Explanations

    high-resolution images related to interior design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adal
    -0.16
    ÃŃž
    -0.15
    orning
    -0.15
     PyErr
    -0.15
    querque
    -0.15
    åħIJ
    -0.14
    uai
    -0.14
    _pw
    -0.14
    Äįe
    -0.14
    ebo
    -0.14
    POSITIVE LOGITS
     gallery
    0.17
     galleries
    0.16
    ÙĪÙĦÙĬÙĪ
    0.15
    igin
    0.15
     collections
    0.15
     resolution
    0.15
    atas
    0.15
     IDE
    0.14
    obuf
    0.14
     galer
    0.14
    Activations Density 0.018%

    No Known Activations