© 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. 8362
    Prev
    Next
    INDEX
    Explanations

    terms related to criminal justice and rehabilitation

    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
    ุà¹Ī
    -0.18
     pás
    -0.16
    merce
    -0.16
    lico
    -0.15
    ugas
    -0.14
    æ»ħ
    -0.14
    urga
    -0.14
    ož
    -0.14
    UF
    -0.13
    cord
    -0.13
    POSITIVE LOGITS
     inmate
    0.29
     prison
    0.28
     prisoner
    0.27
     Prison
    0.26
     inmates
    0.26
     Corrections
    0.24
     prisoners
    0.24
     facility
    0.24
     incarcerated
    0.23
     Facility
    0.23
    Activations Density 0.074%

    No Known Activations