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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2424
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and economic contexts in which outcomes or decisions are evaluated

    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
    SizePolicy
    -0.15
    ahn
    -0.15
    elim
    -0.15
    /front
    -0.14
    jit
    -0.14
    hani
    -0.14
    uko
    -0.14
    ldr
    -0.13
    iyi
    -0.13
    lemen
    -0.13
    POSITIVE LOGITS
     favor
    0.36
     favour
    0.35
     Favor
    0.34
    favor
    0.32
     favors
    0.30
     fav
    0.30
     favorable
    0.22
     Fav
    0.21
     favored
    0.21
     favourable
    0.20
    Activations Density 0.301%

    No Known Activations