© 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. 17-LLAMASCOPE-RES-131K
    11. 74773
    Prev
    Next
    INDEX
    Explanations

    phrases indicating duration or existence in business contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    buie
    -0.07
    mÃŃt
    -0.07
    ocy
    -0.06
    ãĥĵãĥ¼
    -0.06
    ickey
    -0.06
    esus
    -0.06
    otor
    -0.06
    .realm
    -0.06
    ohn
    -0.06
    nez
    -0.06
    POSITIVE LOGITS
     providing
    0.06
     kå
    0.06
    PLE
    0.06
     pleasure
    0.06
    cher
    0.06
    ymi
    0.06
     EVT
    0.06
    ple
    0.06
     placer
    0.06
    iro
    0.06
    Activations Density 0.012%

    No Known Activations