Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 26060
    Prev
    Next
    INDEX
    Explanations

    CSS styles and properties related to link formatting and visual effects

    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
     Trib
    -0.16
    ãĥ¼ãĥľ
    -0.16
    aucoup
    -0.16
     soap
    -0.15
    EMPL
    -0.15
     Soap
    -0.15
    ople
    -0.14
    MLElement
    -0.14
    ebin
    -0.14
    egen
    -0.14
    POSITIVE LOGITS
    Link
    0.32
    link
    0.31
    -link
    0.31
     link
    0.30
    [href
    0.30
    .link
    0.29
     Link
    0.28
    _link
    0.28
     href
    0.27
     textDecoration
    0.27
    Activations Density 0.050%

    No Known Activations