© 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. 27870
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate oppression and hardship

    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
    æ´ŀ
    -0.19
    ä¸ģ
    -0.18
     Doll
    -0.18
     Daw
    -0.17
    ãĥĢ
    -0.17
     dilation
    -0.17
    dart
    -0.17
    (digits
    -0.16
     doll
    -0.16
    doll
    -0.16
    POSITIVE LOGITS
    -de
    1.03
     De
    1.01
    De
    0.99
    de
    0.95
    _de
    0.94
     DE
    0.90
    .de
    0.82
    .De
    0.75
    _De
    0.75
    /de
    0.74
    Activations Density 0.348%

    No Known Activations