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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-LLAMASCOPE-RES-32K
    6. 5854
    Prev
    Next
    INDEX
    Explanations

    references to calls, inquiries, and applications in the context of customer service and recruitment processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ÑĢаÑģпÑĢоÑģÑĤ
    -0.15
    utely
    -0.15
    kus
    -0.15
    achts
    -0.14
     borrowing
    -0.14
    меÑĤÑĮ
    -0.14
    busy
    -0.13
    оÑĢаз
    -0.13
    borrow
    -0.13
    gain
    -0.13
    POSITIVE LOGITS
     received
    0.35
     submitted
    0.33
    received
    0.29
     Received
    0.27
    submitted
    0.26
    Received
    0.26
     recieved
    0.25
     поÑģÑĤÑĥп
    0.25
    Submitted
    0.25
    _received
    0.24
    Activations Density 0.202%

    No Known Activations