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. 25-LLAMASCOPE-RES-32K
    6. 16846
    Prev
    Next
    INDEX
    Explanations

    references to life cycles and their stages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cancel
    -0.17
    eteria
    -0.15
    ChangeEvent
    -0.15
    Cancellation
    -0.15
     Cov
    -0.15
     Cabr
    -0.15
    Cancelled
    -0.14
     Chand
    -0.14
     cogn
    -0.14
    Collapse
    -0.14
    POSITIVE LOGITS
     cycle
    0.69
     cycles
    0.60
     Cycle
    0.59
    cycle
    0.58
    -cycle
    0.55
    Cycle
    0.52
    _cycle
    0.51
    .cycle
    0.49
     ÑĨик
    0.47
    cycles
    0.46
    Activations Density 0.085%

    No Known Activations