© 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. 103
    Prev
    Next
    INDEX
    Explanations

    phrases related to self-care and personal indulgence

    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
    ieg
    -0.06
    缴
    -0.06
    -minute
    -0.06
    ctic
    -0.06
     discre
    -0.06
    Ïģια
    -0.06
    ugar
    -0.05
    _bus
    -0.05
    λεκ
    -0.05
    742
    -0.05
    POSITIVE LOGITS
    obuf
    0.07
    essa
    0.06
    PEG
    0.06
    âĢ¦↵↵↵
    0.06
    .bp
    0.06
    жÑĥ
    0.06
    å¹³æĪIJ
    0.06
    RDD
    0.06
     filme
    0.06
    isse
    0.06
    Activations Density 0.000%

    No Known Activations