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. 28071
    Prev
    Next
    INDEX
    Explanations

    statistical references related to sports performances and standings

    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
     interacts
    -0.15
    leck
    -0.14
     junto
    -0.14
    oho
    -0.14
    ivot
    -0.14
    ekli
    -0.14
    ivor
    -0.14
    qus
    -0.13
     Verd
    -0.13
    اÙĪ
    -0.13
    POSITIVE LOGITS
     mutual
    0.19
     mutually
    0.17
     Mutual
    0.17
     Vys
    0.16
    ushima
    0.15
    Highlights
    0.14
    wang
    0.14
    fcn
    0.13
    .mc
    0.13
    ATTER
    0.13
    Activations Density 0.080%

    No Known Activations