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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-32K
    11. 14179
    Prev
    Next
    INDEX
    Explanations

    punctuations and emphatic expressions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Continue
    -0.16
    chner
    -0.14
    essler
    -0.14
    ä¹Łä¸į
    -0.13
     Continue
    -0.13
    roc
    -0.13
    âĢı
    -0.13
     Toro
    -0.13
    .appspot
    -0.13
    gate
    -0.13
    POSITIVE LOGITS
    Conclusion
    0.28
     Overall
    0.27
     overall
    0.26
    Overall
    0.26
    Hopefully
    0.25
     Hopefully
    0.24
     Conclusion
    0.24
    overall
    0.24
     conclusion
    0.24
     concludes
    0.23
    Activations Density 0.093%

    No Known Activations