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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 2-LLAMASCOPE-RES-32K
    6. 25687
    Prev
    Next
    INDEX
    Explanations

    phrases related to the passage of time and situations that are not going as planned

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tÄĽ
    -0.15
    ãĥ«ãĥĪ
    -0.15
    ój
    -0.15
    orta
    -0.15
    icro
    -0.15
    phere
    -0.14
    ingleton
    -0.14
    alars
    -0.14
    chos
    -0.14
    ukt
    -0.14
    POSITIVE LOGITS
    308
    0.15
    847
    0.14
    ·
    0.14
    if
    0.14
    ={['
    0.14
    rub
    0.14
    576
    0.14
    it
    0.14
    iegel
    0.14
    ham
    0.14
    Activations Density 0.143%

    No Known Activations