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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 2-LLAMASCOPE-RES-32K
    11. 16357
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inç
    -0.15
    vä
    -0.15
    urtles
    -0.15
     {?>↵
    -0.15
    лиÑĤ
    -0.14
    Å¡ov
    -0.14
    sko
    -0.14
    /Foundation
    -0.14
    γκα
    -0.14
     libertin
    -0.14
    POSITIVE LOGITS
     Dual
    0.17
     dual
    0.17
     nut
    0.16
    bjerg
    0.16
    akin
    0.16
    icontrol
    0.15
    529
    0.15
     conf
    0.15
    ãģ¨ãģª
    0.14
     Jack
    0.14
    Activations Density 0.007%

    No Known Activations