© 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. 16-LLAMASCOPE-RES-32K
    11. 9720
    Prev
    Next
    INDEX
    Explanations

    significant contextual phrases and information structures related to location, support, and distinctions

    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
     onCreateView
    -0.14
    ANGED
    -0.14
    .splitContainer
    -0.14
    isky
    -0.13
     Lyn
    -0.13
     ActionTypes
    -0.12
    /banner
    -0.12
     दल
    -0.12
    ãĥ¼ãĥĢ
    -0.12
    _SYM
    -0.12
    POSITIVE LOGITS
    aison
    0.16
    straint
    0.14
    adier
    0.14
    sss
    0.13
     Wit
    0.13
    /met
    0.13
    ahy
    0.13
    ecast
    0.13
    orado
    0.13
    adÃŃ
    0.13
    Activations Density 0.056%

    No Known Activations