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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-LLAMASCOPE-RES-32K
    6. 11383
    Prev
    Next
    INDEX
    Explanations

    expressions of dissatisfaction with services or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    她们
    -0.25
    عÙħاÙĦ
    -0.15
    Ðĩ
    -0.15
    ÑĪила
    -0.14
    ervas
    -0.14
     Heating
    -0.13
    uario
    -0.13
     Healing
    -0.13
    .She
    -0.13
    .sourceforge
    -0.12
    POSITIVE LOGITS
     his
    0.91
     him
    0.81
    ä»ĸ
    0.79
    ä»ĸçļĦ
    0.78
    his
    0.76
     he
    0.75
     емÑĥ
    0.65
     ä»ĸ
    0.65
     его
    0.62
    ï¼Įä»ĸ
    0.62
    Activations Density 2.706%

    No Known Activations