© 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. 30-LLAMASCOPE-RES-32K
    6. 13116
    Prev
    Next
    INDEX
    Explanations

    terms related to performance properties and features of fabrics used in sportswear

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Wheel
    -0.17
     пл
    -0.15
     Wheel
    -0.15
    wheel
    -0.15
     wheel
    -0.15
    ernote
    -0.14
    aiser
    -0.14
    endance
    -0.14
     èIJ
    -0.14
    utm
    -0.13
    POSITIVE LOGITS
     stretch
    0.23
     fabric
    0.21
     Gore
    0.21
     Stretch
    0.21
     fabrics
    0.21
     breath
    0.20
     wind
    0.20
     Breath
    0.19
     ventilation
    0.19
     breathable
    0.19
    Activations Density 0.071%

    No Known Activations