© 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. 2080
    Prev
    Next
    INDEX
    Explanations

    references to illness and death

    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
    aģı
    -0.17
    pointer
    -0.16
    Ptr
    -0.14
     DEAD
    -0.14
     Dead
    -0.14
    agna
    -0.14
    DevExpress
    -0.14
     Pointer
    -0.14
    _construct
    -0.14
    ProcessEvent
    -0.14
    POSITIVE LOGITS
     battle
    0.21
     brave
    0.21
     val
    0.21
     courage
    0.20
     illness
    0.19
     decline
    0.19
     courageous
    0.19
     brav
    0.18
     declining
    0.18
     fight
    0.18
    Activations Density 0.031%

    No Known Activations