© 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. 119549
    Prev
    Next
    INDEX
    Explanations

    phrases related to the nature of reality and perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Transition elements like conjunctions ("and", "that"), punctuation (periods), prepositions ("of", "how"), and knowledge indicators ("know", "aware") that connect ideas or mark sentence boundaries.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    igne
    -0.07
     Sexe
    -0.07
    ileÅŁ
    -0.07
    imdi
    -0.06
    ou
    -0.06
    etc
    -0.06
    reira
    -0.06
    оÑĢони
    -0.06
    orman
    -0.06
    orent
    -0.06
    POSITIVE LOGITS
    265
    0.07
    educt
    0.06
     generally
    0.06
     revolutions
    0.06
     Commons
    0.06
    039
    0.06
     Generally
    0.06
    oola
    0.06
    ìĿ¼ë°ĺ
    0.06
     Сов
    0.06
    Activations Density 0.277%

    No Known Activations