© 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. 16-LLAMASCOPE-RES-32K
    11. 9777
    Prev
    Next
    INDEX
    Explanations

    topics related to school choice and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antz
    -0.17
    adlo
    -0.15
     kli
    -0.15
     Tage
    -0.15
    linger
    -0.14
    اÙĬات
    -0.14
    άνÏī
    -0.14
    akte
    -0.14
    	Copyright
    -0.14
    å¹¹ç·ļ
    -0.14
    POSITIVE LOGITS
     charter
    0.18
     magnet
    0.16
     failing
    0.16
     voucher
    0.16
     founder
    0.15
    ếu
    0.15
     Charter
    0.15
     open
    0.15
     char
    0.15
     Magnet
    0.15
    Activations Density 0.108%

    No Known Activations