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. 18-LLAMASCOPE-RES-32K
    6. 16486
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "real time" along with references to events, conditions, or situations related to timeliness or immediacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĬĻ
    -0.15
    scheme
    -0.15
    rog
    -0.14
     IRQ
    -0.14
    .constraints
    -0.14
    cheme
    -0.14
    -alt
    -0.13
    ocos
    -0.13
    imensional
    -0.13
    .SetValue
    -0.13
    POSITIVE LOGITS
     mode
    0.25
     detail
    0.23
     format
    0.22
     fashion
    0.21
    detail
    0.19
     terms
    0.18
     Mode
    0.17
     isolation
    0.16
    /Gate
    0.16
     circumstances
    0.16
    Activations Density 0.284%

    No Known Activations