© 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. 28-LLAMASCOPE-RES-32K
    11. 21428
    Prev
    Next
    INDEX
    Explanations

    references to health-related government activities or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rani
    -0.16
    reh
    -0.15
    ë©
    -0.15
    ietf
    -0.15
    ohl
    -0.14
    ucion
    -0.14
    rans
    -0.14
    Manip
    -0.13
    Partition
    -0.13
     newY
    -0.13
    POSITIVE LOGITS
     Ministry
    0.60
     ministry
    0.57
     ministries
    0.44
    Min
    0.36
     Minist
    0.35
     minister
    0.34
     Minister
    0.31
     Cabinet
    0.30
     minist
    0.30
     ÐľÐ¸Ð½
    0.29
    Activations Density 0.223%

    No Known Activations