© 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. 24675
    Prev
    Next
    INDEX
    Explanations

    technical issues and troubleshooting questions related to software or programming

    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
     å¹
    -0.15
    Å¡ak
    -0.14
    alon
    -0.14
     manifold
    -0.13
     theo
    -0.13
     Lie
    -0.12
    ina
    -0.12
    erot
    -0.12
     facts
    -0.12
    gzip
    -0.12
    POSITIVE LOGITS
     Propel
    0.15
    OMET
    0.15
    forcer
    0.14
    erro
    0.14
    ,assign
    0.14
    bak
    0.14
     ìłľê°Ģ
    0.13
    hind
    0.13
    gnore
    0.13
     forcibly
    0.13
    Activations Density 0.536%

    No Known Activations