© 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. 9-LLAMASCOPE-RES-32K
    11. 16468
    Prev
    Next
    INDEX
    Explanations

    references to Chicago and its associated cultural elements, events, and notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erva
    -0.15
    ImageContext
    -0.15
    ÑĢоÑĪ
    -0.15
    .gs
    -0.14
    iolet
    -0.14
     Mach
    -0.14
    evin
    -0.14
    ifax
    -0.14
     Ñħол
    -0.14
    ipop
    -0.14
    POSITIVE LOGITS
     Chicago
    0.30
    Chicago
    0.27
     Illinois
    0.27
     chicago
    0.25
     Milwaukee
    0.18
    .sz
    0.17
     Cubs
    0.17
     cytok
    0.16
    Ill
    0.16
    Lake
    0.15
    Activations Density 0.397%

    No Known Activations