© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-32K
    6. 4635
    Prev
    Next
    INDEX
    Explanations

    concepts related to organization and sorting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quate
    -0.14
    ILT
    -0.14
    581
    -0.14
    566
    -0.14
    789
    -0.14
     Beste
    -0.14
    ÑĦÑĤ
    -0.13
    еление
    -0.13
     bundle
    -0.13
     Quint
    -0.13
    POSITIVE LOGITS
     alphabet
    0.29
     alphabetical
    0.26
     Alphabet
    0.23
    alphabet
    0.21
    .sort
    0.19
     alph
    0.18
    ÑģоÑĢ
    0.18
     orderby
    0.18
    phabet
    0.17
    sorted
    0.17
    Activations Density 0.082%

    No Known Activations