© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 17000
    Prev
    Next
    INDEX
    Explanations

    queries related to organizing and managing files or data systems

    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
    風
    -0.12
    uche
    -0.12
     literals
    -0.12
    chedules
    -0.12
    ι
    -0.12
     clearInterval
    -0.11
    é£İ
    -0.11
    ãĥŁãĥ¥
    -0.11
     Kemp
    -0.11
    olen
    -0.11
    POSITIVE LOGITS
     voxel
    0.27
     vox
    0.27
    .nii
    0.25
    vox
    0.25
    ROI
    0.24
     ROI
    0.23
     roi
    0.22
     dataset
    0.21
     Dataset
    0.21
     subjects
    0.21
    Activations Density 0.048%

    No Known Activations