© 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. 18-LLAMASCOPE-RES-32K
    6. 29222
    Prev
    Next
    INDEX
    Explanations

    technical terms related to caching and memory management processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥŃãĥ¼
    -0.17
     ëĦ¤ìĿ´íĬ¸
    -0.17
    ileÅŁ
    -0.15
    abled
    -0.15
    SCII
    -0.15
    .Raw
    -0.15
    FML
    -0.14
    inspace
    -0.14
    ogui
    -0.14
     squ
    -0.14
    POSITIVE LOGITS
     Fay
    0.16
     merge
    0.15
    ead
    0.15
    rey
    0.15
    lek
    0.14
    leme
    0.14
    oracle
    0.14
    mino
    0.14
     wen
    0.14
    acer
    0.13
    Activations Density 0.146%

    No Known Activations