© 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. 20-LLAMASCOPE-RES-32K
    11. 12136
    Prev
    Next
    INDEX
    Explanations

    multiple mentions of certain numerical patterns or repeating information in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eniable
    -0.18
     kostenlose
    -0.13
     latter
    -0.13
    iete
    -0.12
    ropy
    -0.12
    inge
    -0.12
    ocr
    -0.12
    åł¡
    -0.12
    erson
    -0.12
    id
    -0.12
    POSITIVE LOGITS
    /gtest
    0.15
    ADX
    0.14
    ãİ
    0.14
    âĸ²
    0.14
    ÃĦŸ
    0.13
    Ħĸ
    0.13
    .mapbox
    0.13
    OKIE
    0.13
    -LAST
    0.13
    RetVal
    0.13
    Activations Density 0.262%

    No Known Activations