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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 85429
    Prev
    Next
    INDEX
    Explanations

    phrases related to care and responsibility for pets

    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
    ког
    -0.08
    yx
    -0.07
    ernals
    -0.07
     nors
    -0.07
    LEGRO
    -0.07
    rana
    -0.06
    @qq
    -0.06
    omik
    -0.06
    exo
    -0.06
    leton
    -0.06
    POSITIVE LOGITS
     home
    0.07
     Daly
    0.07
     missed
    0.07
    -home
    0.06
     Home
    0.06
     çķĻ
    0.06
    home
    0.06
    ãn
    0.06
    Home
    0.06
     поÑģÑĤÑĥп
    0.06
    Activations Density 0.011%

    No Known Activations