© 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. 16-LLAMASCOPE-RES-32K
    11. 20628
    Prev
    Next
    INDEX
    Explanations

    references to economic incentives in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eria
    -0.16
    xdc
    -0.16
    adir
    -0.15
    iola
    -0.15
    .SerializeObject
    -0.15
    roller
    -0.15
    .Persistent
    -0.15
    handleRequest
    -0.15
    oga
    -0.15
    ilde
    -0.14
    POSITIVE LOGITS
     incentive
    0.31
     incentives
    0.31
     incent
    0.26
     incentiv
    0.24
     motivation
    0.20
     reward
    0.19
     motive
    0.19
     motivations
    0.17
    cant
    0.16
    mot
    0.16
    Activations Density 0.101%

    No Known Activations