© 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. 26-LLAMASCOPE-RES-32K
    11. 28729
    Prev
    Next
    INDEX
    Explanations

    phrases reflecting silence or actions taken in quiet situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .inflate
    -0.15
    estruction
    -0.14
     Protection
    -0.14
     resisted
    -0.13
    Ø´ÙĪ
    -0.13
     unstable
    -0.13
    MBED
    -0.13
    eo
    -0.13
     loos
    -0.13
     unrestricted
    -0.13
    POSITIVE LOGITS
     silent
    0.87
     silence
    0.87
     quiet
    0.79
     Silent
    0.76
    silent
    0.75
     Silence
    0.73
     Quiet
    0.65
    Sil
    0.64
     silenced
    0.62
    quiet
    0.61
    Activations Density 0.287%

    No Known Activations