© 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. 31-LLAMASCOPE-RES-32K
    11. 21810
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to mathematical measures and spectral properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hess
    -0.14
    zman
    -0.14
     configs
    -0.14
     Aerospace
    -0.14
    LAY
    -0.13
     bezier
    -0.13
    \param
    -0.13
    stantiate
    -0.13
    sigmoid
    -0.13
    VisualStyle
    -0.13
    POSITIVE LOGITS
     Murray
    0.27
     von
    0.27
     AF
    0.24
     masa
    0.24
     operator
    0.23
     crossed
    0.22
    von
    0.21
     Elliott
    0.21
     Operator
    0.21
     Toe
    0.21
    Activations Density 0.012%

    No Known Activations