© 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. 29-LLAMASCOPE-RES-32K
    11. 5096
    Prev
    Next
    INDEX
    Explanations

    specific segments of content that are outlining instructions or descriptions of functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ader
    -0.17
    ÅŁÄ±
    -0.16
    ãģĤãĤĭ
    -0.15
    uncated
    -0.14
    quet
    -0.14
    aders
    -0.14
    sus
    -0.13
    oder
    -0.13
    idis
    -0.13
    logen
    -0.13
    POSITIVE LOGITS
     way
    0.32
     includes
    0.24
     alone
    0.22
     can
    0.21
     include
    0.21
     again
    0.21
     latter
    0.20
     step
    0.20
     INCLUDE
    0.19
     then
    0.19
    Activations Density 0.181%

    No Known Activations