© 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. 82779
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the concept of prevention or avoidance

    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
    álo
    -0.08
     Hlav
    -0.08
    ahat
    -0.07
    .IContainer
    -0.07
    æĸ¹åIJij
    -0.07
    alaxy
    -0.07
    иÑĩ
    -0.07
    OKEN
    -0.07
    ãĥ³ãĥķ
    -0.07
    ланд
    -0.07
    POSITIVE LOGITS
     being
    0.11
     becoming
    0.09
     Being
    0.08
    Being
    0.07
    uman
    0.07
     getting
    0.07
    orda
    0.07
    being
    0.07
     further
    0.07
    bec
    0.07
    Activations Density 0.015%

    No Known Activations