© 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. 28-LLAMASCOPE-RES-32K
    11. 30590
    Prev
    Next
    INDEX
    Explanations

    phrases related to governance and transparency in educational institutions

    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
    ollar
    -0.15
    .scalablytyped
    -0.15
    /new
    -0.14
    æľ¬å½ĵ
    -0.14
    à¤Ĺल
    -0.14
    @nate
    -0.13
     poprvé
    -0.13
    future
    -0.13
    oras
    -0.13
    æĪ¸
    -0.13
    POSITIVE LOGITS
     general
    0.21
     steady
    0.20
     constant
    0.19
     consistent
    0.19
     broad
    0.19
     broadly
    0.17
     generally
    0.17
     generalized
    0.17
     occasional
    0.17
     basic
    0.16
    Activations Density 0.394%

    No Known Activations