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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 28110
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions involving integrals and derivatives

    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
    olon
    -0.15
     Dip
    -0.15
    uckles
    -0.15
    .liferay
    -0.14
    uess
    -0.14
    dice
    -0.14
    uz
    -0.14
    irsch
    -0.14
    isoft
    -0.14
    ÃŃs
    -0.14
    POSITIVE LOGITS
     dt
    0.26
    dt
    0.24
    .dt
    0.21
     dx
    0.19
     d
    0.18
     dr
    0.18
    	dt
    0.17
     dy
    0.16
     DT
    0.16
    DT
    0.16
    Activations Density 0.076%

    No Known Activations