© 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. 12-LLAMASCOPE-RES-32K
    11. 5433
    Prev
    Next
    INDEX
    Explanations

    instances of the word "package" and programming-related keywords in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leban
    -0.19
    $__
    -0.16
    agner
    -0.16
    akens
    -0.16
    pany
    -0.15
    ayette
    -0.14
    énom
    -0.14
    ics
    -0.14
    uja
    -0.14
    uger
    -0.14
    POSITIVE LOGITS
    erd
    0.16
     Pied
    0.15
    zed
    0.15
     flush
    0.14
     cle
    0.14
    ering
    0.14
    ||
    0.13
    redit
    0.13
     Thi
    0.13
    imed
    0.13
    Activations Density 0.001%

    No Known Activations