© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 19727
    Prev
    Next
    INDEX
    Explanations

    references to aerial events or actions involving flight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EMA
    -0.16
     inward
    -0.15
    369
    -0.15
    ÑĪов
    -0.14
    dü
    -0.14
    ILLE
    -0.14
    наÑĢ
    -0.14
    ema
    -0.14
    egative
    -0.14
    ijing
    -0.13
    POSITIVE LOGITS
     air
    0.68
     sky
    0.66
    air
    0.59
     skies
    0.57
    -air
    0.52
    sky
    0.49
     Sky
    0.47
     воздÑĥÑħ
    0.46
    Sky
    0.46
     Air
    0.45
    Activations Density 0.131%

    No Known Activations