© 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. 15-LLAMASCOPE-RES-131K
    11. 104104
    Prev
    Next
    INDEX
    Explanations

    references to digital payment systems and telecommunications services

    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
    cox
    -0.06
     prox
    -0.06
    MEA
    -0.06
    uzzi
    -0.06
    row
    -0.06
     speaking
    -0.06
    ovo
    -0.06
     myster
    -0.06
    jan
    -0.06
    OTA
    -0.06
    POSITIVE LOGITS
     Griffith
    0.08
    alth
    0.07
     DÃŃky
    0.07
    .Areas
    0.07
    åħ
    0.07
    سط
    0.07
    LATED
    0.07
    459
    0.07
    PEED
    0.06
     bouquet
    0.06
    Activations Density 0.009%

    No Known Activations