© 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. 31956
    Prev
    Next
    INDEX
    Explanations

    discussions about law and legal principles

    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
     another
    -0.25
     Another
    -0.22
     other
    -0.22
    another
    -0.20
    Another
    -0.20
    åı¦
    -0.19
     same
    -0.19
    åı¦ä¸Ģ
    -0.18
     next
    -0.17
     later
    -0.17
    POSITIVE LOGITS
    ãģ¾ãģļ
    0.38
    first
    0.36
     first
    0.35
     먼ìłĢ
    0.32
    é¦ĸ
    0.32
    First
    0.31
     firstly
    0.29
     é¦ĸ
    0.29
     Firstly
    0.29
     primero
    0.28
    Activations Density 0.207%

    No Known Activations