© 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. 14-LLAMASCOPE-RES-32K
    6. 10064
    Prev
    Next
    INDEX
    Explanations

    phrases that express limitations and notions of achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BitConverter
    -0.16
    алÑĭ
    -0.16
    lix
    -0.15
    perty
    -0.15
    missive
    -0.15
     Shan
    -0.15
    .lv
    -0.14
    744
    -0.14
    hek
    -0.14
    tparam
    -0.13
    POSITIVE LOGITS
    qui
    0.15
    Äħż
    0.15
     down
    0.15
     adult
    0.15
     already
    0.15
     age
    0.14
    loi
    0.14
     particular
    0.14
     "
    0.14
     saturated
    0.14
    Activations Density 0.126%

    No Known Activations