Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 24699
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to governance and political accountability

    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
    ĥ½
    -0.16
     bÃło
    -0.15
    æĶ»
    -0.15
    лл
    -0.14
    iske
    -0.14
    à¸Ħรà¸ļ
    -0.14
    à¥ģब
    -0.14
    pesan
    -0.14
    avan
    -0.14
    _lista
    -0.14
    POSITIVE LOGITS
     after
    0.22
     already
    0.19
     AFTER
    0.17
    after
    0.16
     immediately
    0.16
    Coder
    0.16
     right
    0.15
    inde
    0.15
     después
    0.15
    apr
    0.15
    Activations Density 0.013%

    No Known Activations