© 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. 2-LLAMASCOPE-RES-32K
    11. 18731
    Prev
    Next
    INDEX
    Explanations

    terms related to monitoring and oversight, particularly in the context of watchdog organizations or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enance
    -0.15
    opath
    -0.15
    eyJ
    -0.15
     Olympia
    -0.15
    á»Ļc
    -0.15
    /animate
    -0.14
    queeze
    -0.14
     Parade
    -0.14
    ÑĩиÑĤ
    -0.14
     mans
    -0.14
    POSITIVE LOGITS
    far
    0.15
    lang
    0.14
    qus
    0.14
    utzer
    0.14
     Barrett
    0.14
    ael
    0.14
    ÏĦον
    0.14
    semi
    0.14
    rons
    0.14
    layer
    0.13
    Activations Density 0.002%

    No Known Activations