© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 5758
    Prev
    Next
    INDEX
    Explanations

    concepts related to time and change, particularly how the past influences the present and future

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gross
    -0.18
     Gross
    -0.17
     actionTypes
    -0.16
    OLF
    -0.15
    cheid
    -0.15
    λη
    -0.15
    nem
    -0.15
     Campos
    -0.15
    itched
    -0.15
     gross
    -0.15
    POSITIVE LOGITS
     future
    0.49
    future
    0.42
     Future
    0.41
    Future
    0.40
    _future
    0.36
     futuro
    0.36
     forward
    0.33
    æľªæĿ¥
    0.33
     futures
    0.30
     бÑĥдÑĥÑī
    0.29
    Activations Density 0.131%

    No Known Activations