© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 460
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" across different 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
    asher
    -0.07
    ãģ¼
    -0.07
    chet
    -0.07
    ìĿ¸ì§Ģ
    -0.06
    änder
    -0.06
    athi
    -0.06
    庫
    -0.06
    esiyle
    -0.06
    454
    -0.06
    asan
    -0.06
    POSITIVE LOGITS
     Freund
    0.07
    idan
    0.06
    iki
    0.06
    ikes
    0.06
    onis
    0.06
    rá
    0.06
     Tu
    0.06
    CREMENT
    0.06
    OA
    0.06
    120
    0.06
    Activations Density 0.036%

    No Known Activations