© 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. 61446
    Prev
    Next
    INDEX
    Explanations

    phrases related to the importance of diversity and inclusivity in various 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
    ote
    -0.07
    orte
    -0.07
    æĸŃ
    -0.07
     intel
    -0.07
    iza
    -0.07
     partida
    -0.07
    asso
    -0.07
    æĸ·
    -0.07
    ÑĨион
    -0.07
     ngu
    -0.07
    POSITIVE LOGITS
    _supported
    0.06
     Laure
    0.06
     кожного
    0.06
     recip
    0.05
    arrison
    0.05
    InRange
    0.05
    éĺ
    0.05
    reet
    0.05
    191
    0.05
     Watson
    0.05
    Activations Density 0.003%

    No Known Activations