© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 27-LLAMASCOPE-RES-32K
    11. 2082
    Prev
    Next
    INDEX
    Explanations

    topics related to environmental issues and specifically the ozone layer

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    838
    -0.15
     Alexandria
    -0.14
    .synthetic
    -0.14
     slu
    -0.14
    ãĥ³ãĥij
    -0.13
     Gund
    -0.13
     khá»ķ
    -0.13
     sud
    -0.13
    /storage
    -0.13
    ãĤ¹ãĤ¿ãĥ¼
    -0.13
    POSITIVE LOGITS
     atmosphere
    0.44
     str
    0.34
     trop
    0.32
     Atmos
    0.30
     atmos
    0.30
     аÑĤмоÑģ
    0.30
    osphere
    0.30
     layer
    0.28
     atmospheric
    0.28
     layers
    0.27
    Activations Density 0.035%

    No Known Activations