© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-32K
    11. 1962
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mitt
    -0.16
    AIT
    -0.16
    nowrap
    -0.15
    vala
    -0.14
    ooth
    -0.14
    emon
    -0.14
    nio
    -0.14
     McKin
    -0.13
    aman
    -0.13
    adal
    -0.13
    POSITIVE LOGITS
     Pace
    0.19
     pace
    0.15
    ãĤ¡
    0.15
    PEC
    0.15
    rieve
    0.15
    pace
    0.14
     Tun
    0.14
    primer
    0.14
    ÏĨο
    0.14
     hed
    0.14
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.