© 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. 21526
    Prev
    Next
    INDEX
    Explanations

    mentions of the University of Wisconsin and related terms

    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
    bef
    -0.15
    deÅŁ
    -0.15
    roys
    -0.15
    yectos
    -0.15
    ãĥ«ãĥĪ
    -0.14
    erule
    -0.14
    olut
    -0.14
    eled
    -0.14
    amon
    -0.14
    bfd
    -0.14
    POSITIVE LOGITS
     Madison
    0.30
     Whit
    0.27
    Mad
    0.26
     Stout
    0.26
     mad
    0.22
    -La
    0.22
    -M
    0.21
     Stevens
    0.21
     Superior
    0.21
     River
    0.21
    Activations Density 0.004%

    No Known Activations