© 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. 20015
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate potential or future actions

    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
     closest
    -0.16
     olsun
    -0.15
    closest
    -0.15
    à¥įपन
    -0.14
     nearest
    -0.13
    olem
    -0.13
    ä¸Ģä¸ĭ
    -0.13
     fastest
    -0.13
    ä¹ĭä¸Ģ
    -0.13
     apart
    -0.12
    POSITIVE LOGITS
     further
    0.80
     weitere
    0.70
     additional
    0.70
    æĽ´å¤ļ
    0.67
     more
    0.67
    additional
    0.57
     Further
    0.54
    Further
    0.53
    more
    0.52
     another
    0.52
    Activations Density 0.458%

    No Known Activations