© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15482
    Prev
    Next
    INDEX
    Explanations

    references to airflow, water flow, and environmental factors related to housing conditions

    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
     downstream
    -0.17
     receiving
    -0.16
    ijo
    -0.16
    emi
    -0.15
    addle
    -0.15
     inaugur
    -0.14
     Cly
    -0.14
    otts
    -0.14
    lesh
    -0.14
     immersed
    -0.14
    POSITIVE LOGITS
     entering
    0.22
     enters
    0.21
     enter
    0.18
     passing
    0.18
    Enter
    0.18
     ÙĪارد
    0.18
     Entered
    0.16
    _Enter
    0.16
     Enter
    0.16
     coming
    0.16
    Activations Density 0.135%

    No Known Activations