© 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. 29-LLAMASCOPE-RES-32K
    11. 1322
    Prev
    Next
    INDEX
    Explanations

    complex phrases related to societal issues and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sort
    -0.21
     Solve
    -0.14
    :eq
    -0.14
    ãģĭãģ®
    -0.14
    ãģĭ
    -0.14
    们
    -0.13
    ิà¹Ĥà¸Ļ
    -0.12
    ãģªãģĮãĤī
    -0.12
     yapılacak
    -0.12
    ัà¸Ļว
    -0.12
    POSITIVE LOGITS
     which
    1.29
    which
    1.09
     Which
    1.00
    Which
    0.94
     WHICH
    0.93
     wich
    0.79
    .which
    0.73
     cui
    0.68
     które
    0.67
     коÑĤоÑĢÑĭе
    0.66
    Activations Density 1.475%

    No Known Activations