© 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. 3389
    Prev
    Next
    INDEX
    Explanations

    phrases related to media and publication topics

    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
    ยม
    -0.07
     therefore
    -0.07
    aphore
    -0.06
    人ãģ¯
    -0.06
     donc
    -0.06
    olk
    -0.06
    [][
    -0.06
    รà¸ģ
    -0.06
     daher
    -0.06
    -ÑĤо
    -0.06
    POSITIVE LOGITS
    neath
    0.08
    ếp
    0.07
    ież
    0.07
    наÑģлÑĸдок
    0.07
    äll
    0.07
    æĸ¼
    0.07
     ÑĩиÑģлÑĸ
    0.07
    äºİ
    0.07
    wards
    0.07
    Ñħод
    0.06
    Activations Density 0.023%

    No Known Activations