© 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. 28-LLAMASCOPE-RES-32K
    11. 27404
    Prev
    Next
    INDEX
    Explanations

    specific measurements and dimensions related to objects and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Morgan
    -0.21
    morgan
    -0.20
     Morg
    -0.20
     Miles
    -0.19
     Miz
    -0.19
    mpl
    -0.18
     Mage
    -0.17
     âĹĦ
    -0.17
     Mud
    -0.17
     Mayer
    -0.17
    POSITIVE LOGITS
     mm
    0.68
    mm
    0.66
     MM
    0.54
    -mm
    0.53
     мм
    0.49
    MM
    0.49
    _mm
    0.48
    .mm
    0.47
    мм
    0.42
     um
    0.41
    Activations Density 0.032%

    No Known Activations