© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 28-LLAMASCOPE-RES-32K
    6. 951
    Prev
    Next
    INDEX
    Explanations

    expressions of nervousness or anxiety in professional or public speaking contexts

    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
    affen
    -0.17
    rosso
    -0.16
    .ManyToMany
    -0.15
    kir
    -0.15
    ема
    -0.14
    iani
    -0.14
    zano
    -0.14
    جات
    -0.13
     Unsigned
    -0.13
    dee
    -0.13
    POSITIVE LOGITS
     delivery
    0.31
     presentation
    0.29
     nerves
    0.28
     nervous
    0.28
     Delivery
    0.27
     Presentation
    0.26
     speaking
    0.26
    presentation
    0.25
     presenting
    0.25
     preparation
    0.25
    Activations Density 0.080%

    No Known Activations