© 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. 23-LLAMASCOPE-RES-32K
    11. 1254
    Prev
    Next
    INDEX
    Explanations

    references to academic publications and their statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urls
    -0.15
    å¥ı
    -0.14
    osen
    -0.14
    665
    -0.14
    824
    -0.14
    лÑıв
    -0.13
    persona
    -0.13
    91
    -0.13
    ReadWrite
    -0.12
    cih
    -0.12
    POSITIVE LOGITS
     publication
    0.69
     published
    0.66
     publish
    0.66
     publishing
    0.64
     pub
    0.60
    published
    0.56
    publish
    0.54
     publi
    0.54
    publication
    0.54
    -publish
    0.54
    Activations Density 0.201%

    No Known Activations