© 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. 106820
    Prev
    Next
    INDEX
    Explanations

    prepositions and their related phrases

    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
    ":[{↵
    -0.07
    uin
    -0.07
    engl
    -0.07
    ẹn
    -0.06
    ikk
    -0.06
     ner
    -0.06
    Ø
    -0.06
    ÑĢаг
    -0.06
     LAND
    -0.06
    Ownership
    -0.06
    POSITIVE LOGITS
    uluk
    0.07
    alles
    0.07
    ologna
    0.07
    quier
    0.06
    annie
    0.06
    ekil
    0.06
    sian
    0.06
    keh
    0.06
    annies
    0.06
    anny
    0.06
    Activations Density 0.017%

    No Known Activations