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. 28-LLAMASCOPE-RES-32K
    6. 29573
    Prev
    Next
    INDEX
    Explanations

    phrases related to radar technology and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aeda
    -0.17
    erten
    -0.16
     Afrika
    -0.15
    thinkable
    -0.15
    rell
    -0.14
    ataires
    -0.14
    gli
    -0.14
    distance
    -0.13
     distance
    -0.13
    owan
    -0.13
    POSITIVE LOGITS
     exposures
    0.24
     exposure
    0.23
     Exposure
    0.22
     pointing
    0.22
     instrumental
    0.22
     science
    0.21
     sky
    0.20
    seeing
    0.19
     seeing
    0.18
    sky
    0.17
    Activations Density 0.029%

    No Known Activations