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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 24-LLAMASCOPE-RES-32K
    11. 14156
    Prev
    Next
    INDEX
    Explanations

    questions related to experiences and situations

    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
     your
    -0.70
    your
    -0.66
     YOUR
    -0.59
    ä½łçļĦ
    -0.57
    Your
    -0.56
    æĤ¨çļĦ
    -0.54
     ваÑĪ
    -0.54
    -your
    -0.54
    YOUR
    -0.54
     Your
    -0.53
    POSITIVE LOGITS
     you
    0.54
     You
    0.42
    you
    0.41
    You
    0.39
     bạn
    0.35
    _you
    0.32
     você
    0.30
     à¤Ĩप
    0.30
    -you
    0.29
    ä½ł
    0.28
    Activations Density 0.369%

    No Known Activations