© 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. 11238
    Prev
    Next
    INDEX
    Explanations

    references to university incidents and campus-related events

    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
     remar
    -0.15
    jem
    -0.14
     Indust
    -0.14
     Counties
    -0.13
    -unstyled
    -0.13
    åĩ»
    -0.13
    cen
    -0.13
    å°ijå¹´
    -0.13
     NRL
    -0.13
     sof
    -0.13
    POSITIVE LOGITS
     campus
    0.66
     student
    0.59
     students
    0.56
    -campus
    0.54
     Student
    0.52
     university
    0.52
     Students
    0.51
     Campus
    0.51
    student
    0.49
    ampus
    0.48
    Activations Density 1.027%

    No Known Activations